[PATCH 00/58] staging: lustre: bug fixes from lustre 2.5.[56-58]

[PATCH 00/58] staging: lustre: bug fixes from lustre 2.5.[56-58]

[James Simmons]

Here is the next batch of fixes and cleanups that went into
Lustre from versions 2.5.56 up to 2.5.58. Besides those changes
the patches for LU-3531/LU-4906 were broken into several smaller
patches as required for the staging tree. The rest of the patches
here are minor fixes and some removal of dead or obsolete code.

Chris Horn (1):
  staging: lustre: ptlrpc: Early replies need to honor at_max

Dmitry Eremin (1):
  staging: lustre: lmv: fix issue found by Klocwork Insight tool

Fan Yong (4):
  staging: lustre: obdclass: bug fixes for lu_device_type handling
  staging: lustre: llite: enable clients to inject error for lfsck
  staging: lustre: obdclass: unified flow control interfaces
  staging: lustre: reorder LOV_MAGIC_* definition

Jian Yu (1):
  staging: lustre: obdclass: fix lmd_parse() to handle comma-separated
    NIDs

Jinshan Xiong (3):
  staging: lustre: osc: allow to call brw_commit() multiple times
  staging: lustre: llite: avoid a deadlock in page write
  staging: lustre: lov: handle the case of stripe size is not power 2

John L. Hammond (9):
  staging: lustre: mdc: fixup MDS_SWAP_LAYOUTS ELC handling
  staging: lustre: don't need to const __u64 parameters for
    lustre_idl.h
  staging: lustre: const correct FID/OSTID/... helpers
  staging: lustre: use bool for several function in
    lustre_idl.h/lustre_fid.h
  staging: lustre: simplify inline functions in lustre_fid.h
  staging: lustre: lmv: access lum_stripe_offset as little endian
  staging: lustre: lmv: cleanup req in lmv_getattr_name()
  staging: lustre: lmv: rename request to preq in lmv_getattr_name()
  staging: lustre: move ioctls to lustre_ioctl.h

Nathaniel Clark (1):
  staging: lustre: lmv: Ensure lmv_intent_lookup cleans up reqp

Ryan Haasken (1):
  staging: lustre: libcfs: Only dump log once per sec. to avoid EEXIST

Vitaly Fertman (1):
  staging: lustre: ldlm: flock completion fixes.

wang di (36):
  staging: lustre: obd: expand op_cli_flags
  staging: lustre: obd: rename struct lmv_stripe_md field mea to lmv
  staging: lustre: ptlrpc: remove wirecheck for struct lmv_stripe_md
  staging: lustre: llite: cache directory striping information
  staging: lustre: lmv: add new lmv structures
  staging: lustre: mdc: handle IT_READDIR operations
  staging: lustre: llite: label the debug info
  staging: lustre: llite: pass struct md_op_data to ll_dir_read
  staging: lustre: llite: remove debug message in ll_dir_read
  staging: lustre: llite: reduce indent in ll_dir_read
  staging: lustre: llite: set next only when needed in ll_dir_read
  staging: lustre: llite: handle done flags differently in ll_dir_read
  staging: lustre: llite: change done flag in ll_dir_read to bool
  staging: lustre: llite: rename some variables for ll_dir_read
  staging: lustre: llite: clarify some debug messages for statahead
  staging: lustre: llite: remove code never called
  staging: lustre: llite: pass in __u64 pos for ll_dir_read
  staging: lustre: llite: do post work for statahead in readdir case
  staging: lustre: llite: add md_op_data parameter to ll_get_dir_page
  staging: lustre: llite: remove comment from ll_dir_read
  staging: lustre: llite: style cleanup for llite_internal.h
  staging: lustre: llite: pass inode to ll_release_page
  staging: lustre: llite: change remove parameter to bool
  staging: lustre: mdc: don't take rpc lock for readdir case
  staging: lustre: lmv: remove unused lmv_get_mea function
  staging: lustre: lmv: remove duplicate MAX_HASH_*
  staging: lustre: lmv: change handling of lmv striping information
  staging: lustre: lmv: remove lmv_get_easize
  staging: lustre: lmv: replace obd_free_memmd with lmv_free_memmd
  staging: lustre: create striped directory
  staging: lustre: llite: fix "getdirstripe" to show stripe info
  staging: lustre: delete striped directory
  staging: lustre: add ability to migrate inodes.
  staging: lustre: llite: a few fixes for migration.
  staging: lustre: lmv: lookup remote migrating object in LMV
  staging: lustre: llite: add error handler in inode prepare phase

 .../lustre/include/linux/libcfs/libcfs_fail.h      |    3 +
 drivers/staging/lustre/lnet/libcfs/debug.c         |    9 +-
 drivers/staging/lustre/lnet/libcfs/fail.c          |    6 +-
 drivers/staging/lustre/lustre/fld/fld_request.c    |   55 +--
 drivers/staging/lustre/lustre/include/cl_object.h  |    3 +
 drivers/staging/lustre/lustre/include/lu_object.h  |    3 +-
 .../lustre/lustre/include/lustre/lustre_idl.h      |  250 ++++++--
 .../lustre/lustre/include/lustre/lustre_ioctl.h    |  412 ++++++++++++
 .../lustre/lustre/include/lustre/lustre_user.h     |   39 +-
 drivers/staging/lustre/lustre/include/lustre_dlm.h |   11 +-
 .../lustre/lustre/include/lustre_dlm_flags.h       |   36 +-
 drivers/staging/lustre/lustre/include/lustre_fid.h |   30 +-
 drivers/staging/lustre/lustre/include/lustre_lib.h |  286 +---------
 drivers/staging/lustre/lustre/include/lustre_lmv.h |  130 ++++
 drivers/staging/lustre/lustre/include/lustre_mdc.h |    9 +-
 drivers/staging/lustre/lustre/include/obd.h        |   60 +--
 drivers/staging/lustre/lustre/include/obd_class.h  |   24 +
 .../staging/lustre/lustre/include/obd_support.h    |    5 +
 drivers/staging/lustre/lustre/ldlm/ldlm_flock.c    |   98 +++-
 drivers/staging/lustre/lustre/ldlm/ldlm_lib.c      |    4 +-
 drivers/staging/lustre/lustre/ldlm/ldlm_lock.c     |   23 +-
 drivers/staging/lustre/lustre/ldlm/ldlm_request.c  |   16 +-
 drivers/staging/lustre/lustre/ldlm/ldlm_resource.c |    8 +-
 drivers/staging/lustre/lustre/llite/dir.c          |  471 +++++++++-----
 drivers/staging/lustre/lustre/llite/file.c         |  178 +++++-
 .../staging/lustre/lustre/llite/llite_internal.h   |   49 ++-
 drivers/staging/lustre/lustre/llite/llite_lib.c    |  258 ++++++++-
 drivers/staging/lustre/lustre/llite/llite_nfs.c    |   19 +-
 drivers/staging/lustre/lustre/llite/namei.c        |  104 +++-
 drivers/staging/lustre/lustre/llite/rw.c           |    4 +
 drivers/staging/lustre/lustre/llite/rw26.c         |    5 +-
 drivers/staging/lustre/lustre/llite/statahead.c    |   77 ++-
 drivers/staging/lustre/lustre/llite/vvp_dev.c      |    6 -
 drivers/staging/lustre/lustre/llite/vvp_req.c      |    2 +
 drivers/staging/lustre/lustre/llite/xattr.c        |    7 +-
 drivers/staging/lustre/lustre/lmv/lmv_intent.c     |  287 ++++++++--
 drivers/staging/lustre/lustre/lmv/lmv_internal.h   |   67 ++-
 drivers/staging/lustre/lustre/lmv/lmv_obd.c        |  656 ++++++++++++++++----
 drivers/staging/lustre/lustre/lov/lov_obd.c        |    1 +
 drivers/staging/lustre/lustre/lov/lov_object.c     |    1 +
 drivers/staging/lustre/lustre/lov/lov_page.c       |   11 +-
 drivers/staging/lustre/lustre/mdc/lproc_mdc.c      |   17 +-
 drivers/staging/lustre/lustre/mdc/mdc_internal.h   |    2 -
 drivers/staging/lustre/lustre/mdc/mdc_lib.c        |   66 +--
 drivers/staging/lustre/lustre/mdc/mdc_locks.c      |   21 +-
 drivers/staging/lustre/lustre/mdc/mdc_request.c    |   22 +-
 drivers/staging/lustre/lustre/obdclass/class_obd.c |    8 +-
 drivers/staging/lustre/lustre/obdclass/genops.c    |  132 ++++
 .../lustre/lustre/obdclass/linux/linux-module.c    |    1 +
 drivers/staging/lustre/lustre/obdclass/lu_object.c |   34 +-
 .../staging/lustre/lustre/obdclass/obd_config.c    |    1 +
 drivers/staging/lustre/lustre/obdclass/obd_mount.c |   21 +-
 .../staging/lustre/lustre/obdecho/echo_client.c    |    1 +
 drivers/staging/lustre/lustre/osc/osc_cache.c      |   19 +-
 drivers/staging/lustre/lustre/osc/osc_request.c    |    9 +-
 drivers/staging/lustre/lustre/ptlrpc/client.c      |    8 +-
 drivers/staging/lustre/lustre/ptlrpc/import.c      |   11 +-
 .../staging/lustre/lustre/ptlrpc/pack_generic.c    |   37 ++
 drivers/staging/lustre/lustre/ptlrpc/service.c     |   18 +-
 drivers/staging/lustre/lustre/ptlrpc/wiretest.c    |   33 +-
 60 files changed, 2942 insertions(+), 1242 deletions(-)
 create mode 100644 drivers/staging/lustre/lustre/include/lustre/lustre_ioctl.h
 create mode 100644 drivers/staging/lustre/lustre/include/lustre_lmv.h

[PATCH 01/58] staging: lustre: obd: expand op_cli_flags

[James Simmons]

From: wang di <di.wang@intel.com>

Add new flags for metadata handling. These flags are
related to DNE2 handling.

Signed-off-by: wang di <di.wang@intel.com>
Reviewed-on: http://review.whamcloud.com/7043
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-3531
Reviewed-by: John L. Hammond <john.hammond@intel.com>
Reviewed-by: Jinshan Xiong <jinshan.xiong@intel.com>
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
Signed-off-by: James Simmons <jsimmons@infradead.org>
---
 drivers/staging/lustre/lustre/include/obd.h |    2 ++
 1 files changed, 2 insertions(+), 0 deletions(-)

diff --git a/drivers/staging/lustre/lustre/include/obd.h b/drivers/staging/lustre/lustre/include/obd.h
index a1bc2c4..e6fca90 100644
--- a/drivers/staging/lustre/lustre/include/obd.h
+++ b/drivers/staging/lustre/lustre/include/obd.h
@@ -867,6 +867,8 @@ struct md_op_data {
 enum op_cli_flags {
 	CLI_SET_MEA	= 1 << 0,
 	CLI_RM_ENTRY	= 1 << 1,
+	CLI_HASH64	= BIT(2),
+	CLI_API32	= BIT(3),
 };
 
 struct md_enqueue_info;
-- 
1.7.1

[PATCH 02/58] staging: lustre: obd: rename struct lmv_stripe_md field mea to lmv

[James Simmons]

From: wang di <di.wang@intel.com>

Rename struct lmv_stripe_md in struct lustre_md from mea
to lmv.

Signed-off-by: wang di <di.wang@intel.com>
Reviewed-on: http://review.whamcloud.com/7043
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-3531
Reviewed-by: John L. Hammond <john.hammond@intel.com>
Reviewed-by: Jinshan Xiong <jinshan.xiong@intel.com>
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
Signed-off-by: James Simmons <jsimmons@infradead.org>
---
 drivers/staging/lustre/lustre/include/obd.h     |    2 +-
 drivers/staging/lustre/lustre/lmv/lmv_obd.c     |    4 ++--
 drivers/staging/lustre/lustre/mdc/mdc_request.c |    8 ++++----
 3 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/staging/lustre/lustre/include/obd.h b/drivers/staging/lustre/lustre/include/obd.h
index e6fca90..1575c82 100644
--- a/drivers/staging/lustre/lustre/include/obd.h
+++ b/drivers/staging/lustre/lustre/include/obd.h
@@ -1031,7 +1031,7 @@ enum {
 struct lustre_md {
 	struct mdt_body	 *body;
 	struct lov_stripe_md    *lsm;
-	struct lmv_stripe_md    *mea;
+	struct lmv_stripe_md    *lmv;
 #ifdef CONFIG_FS_POSIX_ACL
 	struct posix_acl	*posix_acl;
 #endif
diff --git a/drivers/staging/lustre/lustre/lmv/lmv_obd.c b/drivers/staging/lustre/lustre/lmv/lmv_obd.c
index 0e1588a..fac04f0 100644
--- a/drivers/staging/lustre/lustre/lmv/lmv_obd.c
+++ b/drivers/staging/lustre/lustre/lmv/lmv_obd.c
@@ -2571,8 +2571,8 @@ static int lmv_free_lustre_md(struct obd_export *exp, struct lustre_md *md)
 	struct lmv_obd	  *lmv = &obd->u.lmv;
 	struct lmv_tgt_desc *tgt = lmv->tgts[0];
 
-	if (md->mea)
-		obd_free_memmd(exp, (void *)&md->mea);
+	if (md->lmv)
+		obd_free_memmd(exp, (void *)&md->lmv);
 	if (!tgt || !tgt->ltd_exp)
 		return -EINVAL;
 	return md_free_lustre_md(tgt->ltd_exp, md);
diff --git a/drivers/staging/lustre/lustre/mdc/mdc_request.c b/drivers/staging/lustre/lustre/mdc/mdc_request.c
index d4cc73b..4fc3f9b 100644
--- a/drivers/staging/lustre/lustre/mdc/mdc_request.c
+++ b/drivers/staging/lustre/lustre/mdc/mdc_request.c
@@ -504,15 +504,15 @@ static int mdc_get_lustre_md(struct obd_export *exp,
 				goto out;
 			}
 
-			rc = obd_unpackmd(md_exp, (void *)&md->mea, lmv,
+			rc = obd_unpackmd(md_exp, (void *)&md->lmv, lmv,
 					  lmvsize);
 			if (rc < 0)
 				goto out;
 
-			if (rc < sizeof(*md->mea)) {
+			if (rc < sizeof(*md->lmv)) {
 				CDEBUG(D_INFO,
-				       "size too small: rc < sizeof(*md->mea) (%d < %d)\n",
-					rc, (int)sizeof(*md->mea));
+				       "size too small: rc < sizeof(*md->lmv) (%d < %d)\n",
+					rc, (int)sizeof(*md->lmv));
 				rc = -EPROTO;
 				goto out;
 			}
-- 
1.7.1

[PATCH 03/58] staging: lustre: ptlrpc: remove wirecheck for struct lmv_stripe_md

[James Simmons]

From: wang di <di.wang@intel.com>

Remove the wiretest check for this data structure.

Signed-off-by: wang di <di.wang@intel.com>
Reviewed-on: http://review.whamcloud.com/7043
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-3531
Reviewed-by: John L. Hammond <john.hammond@intel.com>
Reviewed-by: Jinshan Xiong <jinshan.xiong@intel.com>
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
Signed-off-by: James Simmons <jsimmons@infradead.org>
---
 drivers/staging/lustre/lustre/ptlrpc/wiretest.c |   29 -----------------------
 1 files changed, 0 insertions(+), 29 deletions(-)

diff --git a/drivers/staging/lustre/lustre/ptlrpc/wiretest.c b/drivers/staging/lustre/lustre/ptlrpc/wiretest.c
index 6cc2b2e..4c500a9 100644
--- a/drivers/staging/lustre/lustre/ptlrpc/wiretest.c
+++ b/drivers/staging/lustre/lustre/ptlrpc/wiretest.c
@@ -2617,35 +2617,6 @@ void lustre_assert_wire_constants(void)
 	LASSERTF((int)sizeof(((struct lmv_desc *)0)->ld_uuid) == 40, "found %lld\n",
 		 (long long)(int)sizeof(((struct lmv_desc *)0)->ld_uuid));
 
-	/* Checks for struct lmv_stripe_md */
-	LASSERTF((int)sizeof(struct lmv_stripe_md) == 32, "found %lld\n",
-		 (long long)(int)sizeof(struct lmv_stripe_md));
-	LASSERTF((int)offsetof(struct lmv_stripe_md, mea_magic) == 0, "found %lld\n",
-		 (long long)(int)offsetof(struct lmv_stripe_md, mea_magic));
-	LASSERTF((int)sizeof(((struct lmv_stripe_md *)0)->mea_magic) == 4, "found %lld\n",
-		 (long long)(int)sizeof(((struct lmv_stripe_md *)0)->mea_magic));
-	LASSERTF((int)offsetof(struct lmv_stripe_md, mea_count) == 4, "found %lld\n",
-		 (long long)(int)offsetof(struct lmv_stripe_md, mea_count));
-	LASSERTF((int)sizeof(((struct lmv_stripe_md *)0)->mea_count) == 4, "found %lld\n",
-		 (long long)(int)sizeof(((struct lmv_stripe_md *)0)->mea_count));
-	LASSERTF((int)offsetof(struct lmv_stripe_md, mea_master) == 8, "found %lld\n",
-		 (long long)(int)offsetof(struct lmv_stripe_md, mea_master));
-	LASSERTF((int)sizeof(((struct lmv_stripe_md *)0)->mea_master) == 4, "found %lld\n",
-		 (long long)(int)sizeof(((struct lmv_stripe_md *)0)->mea_master));
-	LASSERTF((int)offsetof(struct lmv_stripe_md, mea_padding) == 12, "found %lld\n",
-		 (long long)(int)offsetof(struct lmv_stripe_md, mea_padding));
-	LASSERTF((int)sizeof(((struct lmv_stripe_md *)0)->mea_padding) == 4, "found %lld\n",
-		 (long long)(int)sizeof(((struct lmv_stripe_md *)0)->mea_padding));
-	CLASSERT(LOV_MAXPOOLNAME == 16);
-	LASSERTF((int)offsetof(struct lmv_stripe_md, mea_pool_name[16]) == 32, "found %lld\n",
-		 (long long)(int)offsetof(struct lmv_stripe_md, mea_pool_name[16]));
-	LASSERTF((int)sizeof(((struct lmv_stripe_md *)0)->mea_pool_name[16]) == 1, "found %lld\n",
-		 (long long)(int)sizeof(((struct lmv_stripe_md *)0)->mea_pool_name[16]));
-	LASSERTF((int)offsetof(struct lmv_stripe_md, mea_ids[0]) == 32, "found %lld\n",
-		 (long long)(int)offsetof(struct lmv_stripe_md, mea_ids[0]));
-	LASSERTF((int)sizeof(((struct lmv_stripe_md *)0)->mea_ids[0]) == 16, "found %lld\n",
-		 (long long)(int)sizeof(((struct lmv_stripe_md *)0)->mea_ids[0]));
-
 	/* Checks for struct lov_desc */
 	LASSERTF((int)sizeof(struct lov_desc) == 88, "found %lld\n",
 		 (long long)(int)sizeof(struct lov_desc));
-- 
1.7.1

[PATCH 04/58] staging: lustre: llite: cache directory striping information

[James Simmons]

From: wang di <di.wang@intel.com>

Cache directory striping information that the clients receive
from the metadata servers.

Signed-off-by: wang di <di.wang@intel.com>
Reviewed-on: http://review.whamcloud.com/7043
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-3531
Reviewed-by: John L. Hammond <john.hammond@intel.com>
Reviewed-by: Jinshan Xiong <jinshan.xiong@intel.com>
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
Signed-off-by: James Simmons <jsimmons@infradead.org>
---
 .../staging/lustre/lustre/llite/llite_internal.h   |    3 +++
 drivers/staging/lustre/lustre/llite/llite_lib.c    |   15 +++++++++++++--
 2 files changed, 16 insertions(+), 2 deletions(-)

diff --git a/drivers/staging/lustre/lustre/llite/llite_internal.h b/drivers/staging/lustre/lustre/llite/llite_internal.h
index 27d3f77..baa208f 100644
--- a/drivers/staging/lustre/lustre/llite/llite_internal.h
+++ b/drivers/staging/lustre/lustre/llite/llite_internal.h
@@ -173,6 +173,8 @@ struct ll_inode_info {
 			 * -- I am the owner of dir statahead.
 			 */
 			pid_t			   d_opendir_pid;
+			/* directory stripe information */
+			struct lmv_stripe_md		*d_lmv_md;
 		} d;
 
 #define lli_readdir_mutex       u.d.d_readdir_mutex
@@ -180,6 +182,7 @@ struct ll_inode_info {
 #define lli_sai		 u.d.d_sai
 #define lli_sa_lock	     u.d.d_sa_lock
 #define lli_opendir_pid	 u.d.d_opendir_pid
+#define lli_lmv_md		u.d.d_lmv_md
 
 		/* for non-directory */
 		struct {
diff --git a/drivers/staging/lustre/lustre/llite/llite_lib.c b/drivers/staging/lustre/lustre/llite/llite_lib.c
index 75d568f..eb715be 100644
--- a/drivers/staging/lustre/lustre/llite/llite_lib.c
+++ b/drivers/staging/lustre/lustre/llite/llite_lib.c
@@ -2090,11 +2090,22 @@ struct md_op_data *ll_prep_md_op_data(struct md_op_data *op_data,
 
 	ll_i2gids(op_data->op_suppgids, i1, i2);
 	op_data->op_fid1 = *ll_inode2fid(i1);
+	if (S_ISDIR(i1->i_mode))
+		op_data->op_mea1 = ll_i2info(i1)->lli_lmv_md;
 
-	if (i2)
+	if (i2) {
 		op_data->op_fid2 = *ll_inode2fid(i2);
-	else
+		if (S_ISDIR(i2->i_mode))
+			op_data->op_mea2 = ll_i2info(i2)->lli_lmv_md;
+	} else {
 		fid_zero(&op_data->op_fid2);
+	}
+
+	if (ll_i2sbi(i1)->ll_flags & LL_SBI_64BIT_HASH)
+		op_data->op_cli_flags |= CLI_HASH64;
+
+	if (ll_need_32bit_api(ll_i2sbi(i1)))
+		op_data->op_cli_flags |= CLI_API32;
 
 	op_data->op_name = name;
 	op_data->op_namelen = namelen;
-- 
1.7.1

[PATCH 05/58] staging: lustre: lmv: add new lmv structures

[James Simmons]

From: wang di <di.wang@intel.com>

Newer lustre version on metadata servers support different
version of lmv magic. This add the new data structures
to handle these new lmv magic versions.

Signed-off-by: wang di <di.wang@intel.com>
Reviewed-on: http://review.whamcloud.com/7043
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-3531
Reviewed-by: John L. Hammond <john.hammond@intel.com>
Reviewed-by: Jinshan Xiong <jinshan.xiong@intel.com>
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
Signed-off-by: James Simmons <jsimmons@infradead.org>
---
 .../lustre/lustre/include/lustre/lustre_idl.h      |   81 +++++++++++++++++---
 drivers/staging/lustre/lustre/include/lustre_lmv.h |   66 ++++++++++++++++
 drivers/staging/lustre/lustre/lmv/lmv_internal.h   |    1 +
 drivers/staging/lustre/lustre/lmv/lmv_obd.c        |    1 +
 drivers/staging/lustre/lustre/mdc/mdc_request.c    |    1 +
 5 files changed, 140 insertions(+), 10 deletions(-)
 create mode 100644 drivers/staging/lustre/lustre/include/lustre_lmv.h

diff --git a/drivers/staging/lustre/lustre/include/lustre/lustre_idl.h b/drivers/staging/lustre/lustre/include/lustre/lustre_idl.h
index 051864c..32471a6 100644
--- a/drivers/staging/lustre/lustre/include/lustre/lustre_idl.h
+++ b/drivers/staging/lustre/lustre/include/lustre/lustre_idl.h
@@ -2482,16 +2482,6 @@ struct lmv_desc {
 	struct obd_uuid ld_uuid;
 };
 
-/* TODO: lmv_stripe_md should contain mds capabilities for all slave fids */
-struct lmv_stripe_md {
-	__u32	 mea_magic;
-	__u32	 mea_count;
-	__u32	 mea_master;
-	__u32	 mea_padding;
-	char	  mea_pool_name[LOV_MAXPOOLNAME];
-	struct lu_fid mea_ids[0];
-};
-
 #define MEA_MAGIC_LAST_CHAR      0xb2221ca1
 #define MEA_MAGIC_ALL_CHARS      0xb222a11c
 #define MEA_MAGIC_HASH_SEGMENT   0xb222a11b
@@ -2500,6 +2490,77 @@ struct lmv_stripe_md {
 #define MAX_HASH_SIZE	    0x7fffffffffffffffULL
 #define MAX_HASH_HIGHEST_BIT     0x1000000000000000ULL
 
+/* lmv structures */
+#define LMV_MAGIC_V1	0x0CD10CD0	/* normal stripe lmv magic */
+#define LMV_USER_MAGIC	0x0CD20CD0	/* default lmv magic*/
+#define LMV_MAGIC	LMV_MAGIC_V1
+struct lmv_mds_md_v1 {
+	__u32 lmv_magic;
+	__u32 lmv_stripe_count;		/* stripe count */
+	__u32 lmv_master_mdt_index;	/* master MDT index */
+	__u32 lmv_hash_type;		/* dir stripe policy, i.e. indicate
+					 * which hash function to be used
+					 */
+	__u32 lmv_layout_version;	/* Used for directory restriping */
+	__u32 lmv_padding;
+	char lmv_pool_name[LOV_MAXPOOLNAME];	/* pool name */
+	struct lu_fid lmv_stripe_fids[0];	/* FIDs for each stripe */
+};
+
+union lmv_mds_md {
+	__u32			lmv_magic;
+	struct lmv_mds_md_v1	lmv_md_v1;
+	struct lmv_user_md	lmv_user_md;
+};
+
+static inline ssize_t lmv_mds_md_size(int stripe_count, unsigned int lmm_magic)
+{
+	ssize_t len = -EINVAL;
+
+	switch (lmm_magic) {
+	case LMV_MAGIC_V1: {
+		struct lmv_mds_md_v1 *lmm1;
+
+		len = sizeof(*lmm1);
+		len += stripe_count * sizeof(lmm1->lmv_stripe_fids[0]);
+		break; }
+	default:
+		break;
+	}
+	return len;
+}
+
+static inline int lmv_mds_md_stripe_count_get(const union lmv_mds_md *lmm)
+{
+	switch (le32_to_cpu(lmm->lmv_magic)) {
+	case LMV_MAGIC_V1:
+		return le32_to_cpu(lmm->lmv_md_v1.lmv_stripe_count);
+	case LMV_USER_MAGIC:
+		return le32_to_cpu(lmm->lmv_user_md.lum_stripe_count);
+	default:
+		return -EINVAL;
+	}
+}
+
+static inline int lmv_mds_md_stripe_count_set(union lmv_mds_md *lmm,
+					      unsigned int stripe_count)
+{
+	int rc = 0;
+
+	switch (le32_to_cpu(lmm->lmv_magic)) {
+	case LMV_MAGIC_V1:
+		lmm->lmv_md_v1.lmv_stripe_count = cpu_to_le32(stripe_count);
+		break;
+	case LMV_USER_MAGIC:
+		lmm->lmv_user_md.lum_stripe_count = cpu_to_le32(stripe_count);
+		break;
+	default:
+		rc = -EINVAL;
+		break;
+	}
+	return rc;
+}
+
 enum fld_rpc_opc {
 	FLD_QUERY	= 900,
 	FLD_READ	= 901,
diff --git a/drivers/staging/lustre/lustre/include/lustre_lmv.h b/drivers/staging/lustre/lustre/include/lustre_lmv.h
new file mode 100644
index 0000000..0620c8c
--- /dev/null
+++ b/drivers/staging/lustre/lustre/include/lustre_lmv.h
@@ -0,0 +1,66 @@
+/*
+ * GPL HEADER START
+ *
+ * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 only,
+ * as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License version 2 for more details.  A copy is
+ * included in the COPYING file that accompanied this code.
+ *
+ * You should have received a copy of the GNU General Public License
+ * version 2 along with this program; If not, see
+ * http://www.sun.com/software/products/lustre/docs/GPLv2.pdf
+ *
+ * GPL HEADER END
+ */
+/*
+ * Copyright (c) 2013, Intel Corporation.
+ */
+/*
+ * lustre/include/lustre_lmv.h
+ *
+ * Lustre LMV structures and functions.
+ *
+ * Author: Di Wang <di.wang@intel.com>
+ */
+
+#ifndef _LUSTRE_LMV_H
+#define _LUSTRE_LMV_H
+#include "lustre/lustre_idl.h"
+
+struct lmv_oinfo {
+	struct lu_fid	lmo_fid;
+	u32		lmo_mds;
+	struct inode	*lmo_root;
+};
+
+struct lmv_stripe_md {
+	__u32	mea_magic;
+	__u32	mea_count;
+	__u32	mea_master;
+	__u32	mea_padding;
+	char	mea_pool_name[LOV_MAXPOOLNAME];
+	struct lu_fid mea_ids[0];
+};
+
+union lmv_mds_md;
+
+int lmv_unpack_md(struct obd_export *exp, struct lmv_stripe_md **lsmp,
+		  const union lmv_mds_md *lmm, int stripe_count);
+
+static inline int lmv_alloc_memmd(struct lmv_stripe_md **lsmp, int stripe_count)
+{
+	return lmv_unpack_md(NULL, lsmp, NULL, stripe_count);
+}
+
+static inline void lmv_free_memmd(struct lmv_stripe_md *lsm)
+{
+	lmv_unpack_md(NULL, &lsm, NULL, 0);
+}
+#endif
diff --git a/drivers/staging/lustre/lustre/lmv/lmv_internal.h b/drivers/staging/lustre/lustre/lmv/lmv_internal.h
index 0beafc4..471470b 100644
--- a/drivers/staging/lustre/lustre/lmv/lmv_internal.h
+++ b/drivers/staging/lustre/lustre/lmv/lmv_internal.h
@@ -35,6 +35,7 @@
 
 #include "../include/lustre/lustre_idl.h"
 #include "../include/obd.h"
+#include "../include/lustre_lmv.h"
 
 #define LMV_MAX_TGT_COUNT 128
 
diff --git a/drivers/staging/lustre/lustre/lmv/lmv_obd.c b/drivers/staging/lustre/lustre/lmv/lmv_obd.c
index fac04f0..8e83263 100644
--- a/drivers/staging/lustre/lustre/lmv/lmv_obd.c
+++ b/drivers/staging/lustre/lustre/lmv/lmv_obd.c
@@ -46,6 +46,7 @@
 #include "../include/lustre_lib.h"
 #include "../include/lustre_net.h"
 #include "../include/obd_class.h"
+#include "../include/lustre_lmv.h"
 #include "../include/lprocfs_status.h"
 #include "../include/lustre_lite.h"
 #include "../include/lustre_fid.h"
diff --git a/drivers/staging/lustre/lustre/mdc/mdc_request.c b/drivers/staging/lustre/lustre/mdc/mdc_request.c
index 4fc3f9b..ab78754 100644
--- a/drivers/staging/lustre/lustre/mdc/mdc_request.c
+++ b/drivers/staging/lustre/lustre/mdc/mdc_request.c
@@ -40,6 +40,7 @@
 
 #include "../include/lustre_acl.h"
 #include "../include/obd_class.h"
+#include "../include/lustre_lmv.h"
 #include "../include/lustre_fid.h"
 #include "../include/lprocfs_status.h"
 #include "../include/lustre_param.h"
-- 
1.7.1

[PATCH 06/58] staging: lustre: mdc: handle IT_READDIR operations

[James Simmons]

From: wang di <di.wang@intel.com>

The readdir operations lock was incomplete. This
patch fills in the missing pieces.

Signed-off-by: wang di <di.wang@intel.com>
Reviewed-on: http://review.whamcloud.com/7043
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-3531
Reviewed-by: John L. Hammond <john.hammond@intel.com>
Reviewed-by: Jinshan Xiong <jinshan.xiong@intel.com>
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
Signed-off-by: James Simmons <jsimmons@infradead.org>
---
 drivers/staging/lustre/lustre/include/obd.h   |    4 +++-
 drivers/staging/lustre/lustre/mdc/mdc_locks.c |    8 +++++++-
 2 files changed, 10 insertions(+), 2 deletions(-)

diff --git a/drivers/staging/lustre/lustre/include/obd.h b/drivers/staging/lustre/lustre/include/obd.h
index 1575c82..17b8d22 100644
--- a/drivers/staging/lustre/lustre/include/obd.h
+++ b/drivers/staging/lustre/lustre/include/obd.h
@@ -801,9 +801,11 @@ static inline int it_to_lock_mode(struct lookup_intent *it)
 	/* CREAT needs to be tested before open (both could be set) */
 	if (it->it_op & IT_CREAT)
 		return LCK_CW;
-	else if (it->it_op & (IT_READDIR | IT_GETATTR | IT_OPEN | IT_LOOKUP |
+	else if (it->it_op & (IT_GETATTR | IT_OPEN | IT_LOOKUP |
 			      IT_LAYOUT))
 		return LCK_CR;
+	else if (it->it_op & IT_READDIR)
+		return LCK_PR;
 	else if (it->it_op &  IT_GETXATTR)
 		return LCK_PR;
 	else if (it->it_op &  IT_SETXATTR)
diff --git a/drivers/staging/lustre/lustre/mdc/mdc_locks.c b/drivers/staging/lustre/lustre/mdc/mdc_locks.c
index f48b584..06a1274 100644
--- a/drivers/staging/lustre/lustre/mdc/mdc_locks.c
+++ b/drivers/staging/lustre/lustre/mdc/mdc_locks.c
@@ -903,6 +903,9 @@ static int mdc_finish_intent_lock(struct obd_export *exp,
 	LASSERT(request != LP_POISON);
 	LASSERT(request->rq_repmsg != LP_POISON);
 
+	if (it->it_op & IT_READDIR)
+		return 0;
+
 	if (!it_disposition(it, DISP_IT_EXECD)) {
 		/* The server failed before it even started executing the
 		 * intent, i.e. because it couldn't unpack the request.
@@ -1042,6 +1045,9 @@ int mdc_revalidate_lock(struct obd_export *exp, struct lookup_intent *it,
 						  MDS_INODELOCK_LOOKUP |
 						  MDS_INODELOCK_PERM;
 			break;
+		case IT_READDIR:
+			policy.l_inodebits.bits = MDS_INODELOCK_UPDATE;
+			break;
 		case IT_LAYOUT:
 			policy.l_inodebits.bits = MDS_INODELOCK_LAYOUT;
 			break;
@@ -1119,7 +1125,7 @@ int mdc_intent_lock(struct obd_export *exp, struct md_op_data *op_data,
 
 	lockh.cookie = 0;
 	if (fid_is_sane(&op_data->op_fid2) &&
-	    (it->it_op & (IT_LOOKUP | IT_GETATTR))) {
+	    (it->it_op & (IT_LOOKUP | IT_GETATTR | IT_READDIR))) {
 		/* We could just return 1 immediately, but since we should only
 		 * be called in revalidate_it if we already have a lock, let's
 		 * verify that.
-- 
1.7.1

[PATCH 07/58] staging: lustre: llite: label the debug info

[James Simmons]

From: wang di <di.wang@intel.com>

We report the inode size but never print in the debug
message that the number reported is the size.

Signed-off-by: wang di <di.wang@intel.com>
Reviewed-on: http://review.whamcloud.com/7043
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-3531
Reviewed-by: John L. Hammond <john.hammond@intel.com>
Reviewed-by: Jinshan Xiong <jinshan.xiong@intel.com>
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
Signed-off-by: James Simmons <jsimmons@infradead.org>
---
 drivers/staging/lustre/lustre/llite/dir.c |    2 +-
 1 files changed, 1 insertions(+), 1 deletions(-)

diff --git a/drivers/staging/lustre/lustre/llite/dir.c b/drivers/staging/lustre/lustre/llite/dir.c
index 5b38177..4d81a64 100644
--- a/drivers/staging/lustre/lustre/llite/dir.c
+++ b/drivers/staging/lustre/lustre/llite/dir.c
@@ -615,7 +615,7 @@ static int ll_readdir(struct file *filp, struct dir_context *ctx)
 	int			api32	= ll_need_32bit_api(sbi);
 	int			rc;
 
-	CDEBUG(D_VFSTRACE, "VFS Op:inode="DFID"(%p) pos %lu/%llu 32bit_api %d\n",
+	CDEBUG(D_VFSTRACE, "VFS Op:inode="DFID"(%p) pos/size %lu/%llu 32bit_api %d\n",
 	       PFID(ll_inode2fid(inode)), inode, (unsigned long)pos,
 	       i_size_read(inode), api32);
 
-- 
1.7.1

[PATCH 08/58] staging: lustre: llite: pass struct md_op_data to ll_dir_read

[James Simmons]

From: wang di <di.wang@intel.com>

Add struct md_op_data as a parameter to ll_dir_read.

Signed-off-by: wang di <di.wang@intel.com>
Reviewed-on: http://review.whamcloud.com/7043
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-3531
Reviewed-by: John L. Hammond <john.hammond@intel.com>
Reviewed-by: Jinshan Xiong <jinshan.xiong@intel.com>
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
Signed-off-by: James Simmons <jsimmons@infradead.org>
---
 drivers/staging/lustre/lustre/llite/dir.c          |   14 ++++++++++++--
 .../staging/lustre/lustre/llite/llite_internal.h   |    3 ++-
 drivers/staging/lustre/lustre/llite/llite_nfs.c    |   11 ++++++++++-
 drivers/staging/lustre/lustre/llite/statahead.c    |    7 +++++++
 4 files changed, 31 insertions(+), 4 deletions(-)

diff --git a/drivers/staging/lustre/lustre/llite/dir.c b/drivers/staging/lustre/lustre/llite/dir.c
index 4d81a64..75d0176 100644
--- a/drivers/staging/lustre/lustre/llite/dir.c
+++ b/drivers/staging/lustre/lustre/llite/dir.c
@@ -489,7 +489,8 @@ static __u16 ll_dirent_type_get(struct lu_dirent *ent)
 	return type;
 }
 
-int ll_dir_read(struct inode *inode, struct dir_context *ctx)
+int ll_dir_read(struct inode *inode, struct md_op_data *op_data,
+		struct dir_context *ctx)
 {
 	struct ll_inode_info *info       = ll_i2info(inode);
 	struct ll_sb_info    *sbi	= ll_i2sbi(inode);
@@ -613,6 +614,7 @@ static int ll_readdir(struct file *filp, struct dir_context *ctx)
 	__u64 pos = lfd ? lfd->lfd_pos : 0;
 	int			hash64	= sbi->ll_flags & LL_SBI_64BIT_HASH;
 	int			api32	= ll_need_32bit_api(sbi);
+	struct md_op_data *op_data;
 	int			rc;
 
 	CDEBUG(D_VFSTRACE, "VFS Op:inode="DFID"(%p) pos/size %lu/%llu 32bit_api %d\n",
@@ -627,8 +629,15 @@ static int ll_readdir(struct file *filp, struct dir_context *ctx)
 		goto out;
 	}
 
+	op_data = ll_prep_md_op_data(NULL, inode, inode, NULL, 0, 0,
+				     LUSTRE_OPC_ANY, inode);
+	if (IS_ERR(op_data)) {
+		rc = PTR_ERR(op_data);
+		goto out;
+	}
+
 	ctx->pos = pos;
-	rc = ll_dir_read(inode, ctx);
+	rc = ll_dir_read(inode, op_data, ctx);
 	if (lfd)
 		lfd->lfd_pos = ctx->pos;
 	if (ctx->pos == MDS_DIR_END_OFF) {
@@ -640,6 +649,7 @@ static int ll_readdir(struct file *filp, struct dir_context *ctx)
 		if (api32 && hash64)
 			ctx->pos >>= 32;
 	}
+	ll_finish_md_op_data(op_data);
 	filp->f_version = inode->i_version;
 
 out:
diff --git a/drivers/staging/lustre/lustre/llite/llite_internal.h b/drivers/staging/lustre/lustre/llite/llite_internal.h
index baa208f..623455f 100644
--- a/drivers/staging/lustre/lustre/llite/llite_internal.h
+++ b/drivers/staging/lustre/lustre/llite/llite_internal.h
@@ -653,7 +653,8 @@ extern const struct file_operations ll_dir_operations;
 extern const struct inode_operations ll_dir_inode_operations;
 struct page *ll_get_dir_page(struct inode *dir, __u64 hash,
 			     struct ll_dir_chain *chain);
-int ll_dir_read(struct inode *inode, struct dir_context *ctx);
+int ll_dir_read(struct inode *inode, struct md_op_data *op_data,
+		struct dir_context *ctx);
 
 int ll_get_mdt_idx(struct inode *inode);
 /* llite/namei.c */
diff --git a/drivers/staging/lustre/lustre/llite/llite_nfs.c b/drivers/staging/lustre/lustre/llite/llite_nfs.c
index 65972c8..b74582a 100644
--- a/drivers/staging/lustre/lustre/llite/llite_nfs.c
+++ b/drivers/staging/lustre/lustre/llite/llite_nfs.c
@@ -255,6 +255,7 @@ static int ll_get_name(struct dentry *dentry, char *name,
 		.lgd_fid = ll_i2info(d_inode(child))->lli_fid,
 		.ctx.actor = ll_nfs_get_name_filldir,
 	};
+	struct md_op_data *op_data;
 
 	if (!dir || !S_ISDIR(dir->i_mode)) {
 		rc = -ENOTDIR;
@@ -266,9 +267,17 @@ static int ll_get_name(struct dentry *dentry, char *name,
 		goto out;
 	}
 
+	op_data = ll_prep_md_op_data(NULL, dir, dir, NULL, 0, 0,
+				     LUSTRE_OPC_ANY, dir);
+	if (IS_ERR(op_data)) {
+		rc = PTR_ERR(op_data);
+		goto out;
+	}
+
 	inode_lock(dir);
-	rc = ll_dir_read(dir, &lgd.ctx);
+	rc = ll_dir_read(dir, op_data, &lgd.ctx);
 	inode_unlock(dir);
+	ll_finish_md_op_data(op_data);
 	if (!rc && !lgd.lgd_found)
 		rc = -ENOENT;
 out:
diff --git a/drivers/staging/lustre/lustre/llite/statahead.c b/drivers/staging/lustre/lustre/llite/statahead.c
index f775242..7a7b11c 100644
--- a/drivers/staging/lustre/lustre/llite/statahead.c
+++ b/drivers/staging/lustre/lustre/llite/statahead.c
@@ -1037,6 +1037,7 @@ static int ll_statahead_thread(void *arg)
 	__u64		     pos    = 0;
 	int		       first  = 0;
 	int		       rc     = 0;
+	struct md_op_data *op_data;
 	struct ll_dir_chain       chain;
 	struct l_wait_info	lwi    = { 0 };
 
@@ -1044,6 +1045,11 @@ static int ll_statahead_thread(void *arg)
 	CDEBUG(D_READA, "statahead thread starting: sai %p, parent %pd\n",
 	       sai, parent);
 
+	op_data = ll_prep_md_op_data(NULL, dir, dir, NULL, 0, 0,
+				     LUSTRE_OPC_ANY, dir);
+	if (IS_ERR(op_data))
+		return PTR_ERR(op_data);
+
 	if (sbi->ll_flags & LL_SBI_AGL_ENABLED)
 		ll_start_agl(parent, sai);
 
@@ -1234,6 +1240,7 @@ do_it:
 	}
 
 out:
+	ll_finish_md_op_data(op_data);
 	if (sai->sai_agl_valid) {
 		spin_lock(&plli->lli_agl_lock);
 		thread_set_flags(agl_thread, SVC_STOPPING);
-- 
1.7.1

[PATCH 09/58] staging: lustre: llite: remove debug message in ll_dir_read

[James Simmons]

From: wang di <di.wang@intel.com>

Remove debug message and struct ll_inode_info.

Signed-off-by: wang di <di.wang@intel.com>
Reviewed-on: http://review.whamcloud.com/10761
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-4906
Reviewed-by: John L. Hammond <john.hammond@intel.com>
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
Signed-off-by: James Simmons <jsimmons@infradead.org>
---
 drivers/staging/lustre/lustre/llite/dir.c |    3 ---
 1 files changed, 0 insertions(+), 3 deletions(-)

diff --git a/drivers/staging/lustre/lustre/llite/dir.c b/drivers/staging/lustre/lustre/llite/dir.c
index 75d0176..5b46dd8 100644
--- a/drivers/staging/lustre/lustre/llite/dir.c
+++ b/drivers/staging/lustre/lustre/llite/dir.c
@@ -492,7 +492,6 @@ static __u16 ll_dirent_type_get(struct lu_dirent *ent)
 int ll_dir_read(struct inode *inode, struct md_op_data *op_data,
 		struct dir_context *ctx)
 {
-	struct ll_inode_info *info       = ll_i2info(inode);
 	struct ll_sb_info    *sbi	= ll_i2sbi(inode);
 	__u64		   pos		= ctx->pos;
 	int		   api32      = ll_need_32bit_api(sbi);
@@ -596,8 +595,6 @@ int ll_dir_read(struct inode *inode, struct md_op_data *op_data,
 			}
 		} else {
 			rc = PTR_ERR(page);
-			CERROR("error reading dir "DFID" at %lu: rc %d\n",
-			       PFID(&info->lli_fid), (unsigned long)pos, rc);
 		}
 	}
 
-- 
1.7.1

[PATCH 10/58] staging: lustre: llite: reduce indent in ll_dir_read

[James Simmons]

From: wang di <di.wang@intel.com>

Instead of making a large chunk of code conditional
based on if a page is valid we reverse the page
validity test and exit the loop if the page is invalid
instead. This allows a section of code to reduce its
indentation one level.

Signed-off-by: wang di <di.wang@intel.com>
Reviewed-on: http://review.whamcloud.com/10761
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-4906
Reviewed-by: John L. Hammond <john.hammond@intel.com>
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
Signed-off-by: James Simmons <jsimmons@infradead.org>
---
 drivers/staging/lustre/lustre/llite/dir.c |  147 ++++++++++++++---------------
 1 files changed, 72 insertions(+), 75 deletions(-)

diff --git a/drivers/staging/lustre/lustre/llite/dir.c b/drivers/staging/lustre/lustre/llite/dir.c
index 5b46dd8..77fadf1 100644
--- a/drivers/staging/lustre/lustre/llite/dir.c
+++ b/drivers/staging/lustre/lustre/llite/dir.c
@@ -508,93 +508,90 @@ int ll_dir_read(struct inode *inode, struct md_op_data *op_data,
 	while (rc == 0 && !done) {
 		struct lu_dirpage *dp;
 		struct lu_dirent  *ent;
+		__u64 hash;
+		__u64 next;
+
+		if (IS_ERR(page)) {
+			rc = PTR_ERR(page);
+			break;
+		}
+
+		hash = MDS_DIR_END_OFF;
+		dp = page_address(page);
+		for (ent = lu_dirent_start(dp); ent && !done;
+		     ent = lu_dirent_next(ent)) {
+			__u16	  type;
+			int	    namelen;
+			struct lu_fid  fid;
+			__u64	  lhash;
+			__u64	  ino;
 
-		if (!IS_ERR(page)) {
 			/*
-			 * If page is empty (end of directory is reached),
-			 * use this value.
+			 * XXX: implement correct swabbing here.
 			 */
-			__u64 hash = MDS_DIR_END_OFF;
-			__u64 next;
-
-			dp = page_address(page);
-			for (ent = lu_dirent_start(dp); ent && !done;
-			     ent = lu_dirent_next(ent)) {
-				__u16	  type;
-				int	    namelen;
-				struct lu_fid  fid;
-				__u64	  lhash;
-				__u64	  ino;
 
+			hash = le64_to_cpu(ent->lde_hash);
+			if (hash < pos)
 				/*
-				 * XXX: implement correct swabbing here.
+				 * Skip until we find target hash
+				 * value.
 				 */
+				continue;
 
-				hash = le64_to_cpu(ent->lde_hash);
-				if (hash < pos)
-					/*
-					 * Skip until we find target hash
-					 * value.
-					 */
-					continue;
-
-				namelen = le16_to_cpu(ent->lde_namelen);
-				if (namelen == 0)
-					/*
-					 * Skip dummy record.
-					 */
-					continue;
-
-				if (api32 && hash64)
-					lhash = hash >> 32;
-				else
-					lhash = hash;
-				fid_le_to_cpu(&fid, &ent->lde_fid);
-				ino = cl_fid_build_ino(&fid, api32);
-				type = ll_dirent_type_get(ent);
-				ctx->pos = lhash;
-				/* For 'll_nfs_get_name_filldir()', it will try
-				 * to access the 'ent' through its 'lde_name',
-				 * so the parameter 'name' for 'ctx->actor()'
-				 * must be part of the 'ent'.
+			namelen = le16_to_cpu(ent->lde_namelen);
+			if (namelen == 0)
+				/*
+				 * Skip dummy record.
 				 */
-				done = !dir_emit(ctx, ent->lde_name,
-						 namelen, ino, type);
-			}
-			next = le64_to_cpu(dp->ldp_hash_end);
-			if (!done) {
-				pos = next;
-				if (pos == MDS_DIR_END_OFF) {
-					/*
-					 * End of directory reached.
-					 */
-					done = 1;
-					ll_release_page(page, 0);
-				} else if (1 /* chain is exhausted*/) {
-					/*
-					 * Normal case: continue to the next
-					 * page.
-					 */
-					ll_release_page(page,
-					    le32_to_cpu(dp->ldp_flags) &
-							LDF_COLLIDE);
-					next = pos;
-					page = ll_get_dir_page(inode, pos,
-							       &chain);
-				} else {
-					/*
-					 * go into overflow page.
-					 */
-					LASSERT(le32_to_cpu(dp->ldp_flags) &
+				continue;
+
+			if (api32 && hash64)
+				lhash = hash >> 32;
+			else
+				lhash = hash;
+			fid_le_to_cpu(&fid, &ent->lde_fid);
+			ino = cl_fid_build_ino(&fid, api32);
+			type = ll_dirent_type_get(ent);
+			ctx->pos = lhash;
+			/* For 'll_nfs_get_name_filldir()', it will try
+			 * to access the 'ent' through its 'lde_name',
+			 * so the parameter 'name' for 'ctx->actor()'
+			 * must be part of the 'ent'.
+			 */
+			done = !dir_emit(ctx, ent->lde_name,
+					 namelen, ino, type);
+		}
+		next = le64_to_cpu(dp->ldp_hash_end);
+		if (!done) {
+			pos = next;
+			if (pos == MDS_DIR_END_OFF) {
+				/*
+				 * End of directory reached.
+				 */
+				done = 1;
+				ll_release_page(page, 0);
+			} else if (1 /* chain is exhausted*/) {
+				/*
+				 * Normal case: continue to the next
+				 * page.
+				 */
+				ll_release_page(page,
+						le32_to_cpu(dp->ldp_flags) &
 						LDF_COLLIDE);
-					ll_release_page(page, 1);
-				}
+				next = pos;
+				page = ll_get_dir_page(inode, pos,
+						       &chain);
 			} else {
-				pos = hash;
-				ll_release_page(page, 0);
+				/*
+				 * go into overflow page.
+				 */
+				LASSERT(le32_to_cpu(dp->ldp_flags) &
+					LDF_COLLIDE);
+				ll_release_page(page, 1);
 			}
 		} else {
-			rc = PTR_ERR(page);
+			pos = hash;
+			ll_release_page(page, 0);
 		}
 	}
 
-- 
1.7.1

[PATCH 11/58] staging: lustre: llite: set next only when needed in ll_dir_read

[James Simmons]

From: wang di <di.wang@intel.com>

The variable next needs only to be set when done is false.

Signed-off-by: wang di <di.wang@intel.com>
Reviewed-on: http://review.whamcloud.com/10761
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-4906
Reviewed-by: John L. Hammond <john.hammond@intel.com>
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
Signed-off-by: James Simmons <jsimmons@infradead.org>
---
 drivers/staging/lustre/lustre/llite/dir.c |    3 ++-
 1 files changed, 2 insertions(+), 1 deletions(-)

diff --git a/drivers/staging/lustre/lustre/llite/dir.c b/drivers/staging/lustre/lustre/llite/dir.c
index 77fadf1..48eacee 100644
--- a/drivers/staging/lustre/lustre/llite/dir.c
+++ b/drivers/staging/lustre/lustre/llite/dir.c
@@ -561,8 +561,9 @@ int ll_dir_read(struct inode *inode, struct md_op_data *op_data,
 			done = !dir_emit(ctx, ent->lde_name,
 					 namelen, ino, type);
 		}
-		next = le64_to_cpu(dp->ldp_hash_end);
+
 		if (!done) {
+			next = le64_to_cpu(dp->ldp_hash_end);
 			pos = next;
 			if (pos == MDS_DIR_END_OFF) {
 				/*
-- 
1.7.1

[PATCH 12/58] staging: lustre: llite: handle done flags differently in ll_dir_read

[James Simmons]

From: wang di <di.wang@intel.com>

Invert the done flag test to reduce the code indentation.
If done is true release the page and break out of the
while loop.

Signed-off-by: wang di <di.wang@intel.com>
Reviewed-on: http://review.whamcloud.com/10761
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-4906
Reviewed-by: John L. Hammond <john.hammond@intel.com>
Reviewed-by: Jinshan Xiong <jinshan.xiong@intel.com>
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
Signed-off-by: James Simmons <jsimmons@infradead.org>
---
 drivers/staging/lustre/lustre/llite/dir.c |   59 +++++++++++++++--------------
 1 files changed, 30 insertions(+), 29 deletions(-)

diff --git a/drivers/staging/lustre/lustre/llite/dir.c b/drivers/staging/lustre/lustre/llite/dir.c
index 48eacee..e4d3176 100644
--- a/drivers/staging/lustre/lustre/llite/dir.c
+++ b/drivers/staging/lustre/lustre/llite/dir.c
@@ -562,37 +562,38 @@ int ll_dir_read(struct inode *inode, struct md_op_data *op_data,
 					 namelen, ino, type);
 		}
 
-		if (!done) {
-			next = le64_to_cpu(dp->ldp_hash_end);
-			pos = next;
-			if (pos == MDS_DIR_END_OFF) {
-				/*
-				 * End of directory reached.
-				 */
-				done = 1;
-				ll_release_page(page, 0);
-			} else if (1 /* chain is exhausted*/) {
-				/*
-				 * Normal case: continue to the next
-				 * page.
-				 */
-				ll_release_page(page,
-						le32_to_cpu(dp->ldp_flags) &
-						LDF_COLLIDE);
-				next = pos;
-				page = ll_get_dir_page(inode, pos,
-						       &chain);
-			} else {
-				/*
-				 * go into overflow page.
-				 */
-				LASSERT(le32_to_cpu(dp->ldp_flags) &
-					LDF_COLLIDE);
-				ll_release_page(page, 1);
-			}
-		} else {
+		if (done) {
 			pos = hash;
 			ll_release_page(page, 0);
+			break;
+		}
+
+		next = le64_to_cpu(dp->ldp_hash_end);
+		pos = next;
+		if (pos == MDS_DIR_END_OFF) {
+			/*
+			 * End of directory reached.
+			 */
+			done = 1;
+			ll_release_page(page, 0);
+		} else if (1 /* chain is exhausted*/) {
+			/*
+			 * Normal case: continue to the next
+			 * page.
+			 */
+			ll_release_page(page,
+					le32_to_cpu(dp->ldp_flags) &
+					LDF_COLLIDE);
+			next = pos;
+			page = ll_get_dir_page(inode, pos,
+					       &chain);
+		} else {
+			/*
+			 * go into overflow page.
+			 */
+			LASSERT(le32_to_cpu(dp->ldp_flags) &
+				LDF_COLLIDE);
+			ll_release_page(page, 1);
 		}
 	}
 
-- 
1.7.1

[PATCH 13/58] staging: lustre: llite: change done flag in ll_dir_read to bool

[James Simmons]

From: wang di <di.wang@intel.com>

Change the done flag from integer to bool.

Signed-off-by: wang di <di.wang@intel.com>
Reviewed-on: http://review.whamcloud.com/10761
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-4906
Reviewed-by: John L. Hammond <john.hammond@intel.com>
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
Signed-off-by: James Simmons <jsimmons@infradead.org>
---
 drivers/staging/lustre/lustre/llite/dir.c |    2 +-
 1 files changed, 1 insertions(+), 1 deletions(-)

diff --git a/drivers/staging/lustre/lustre/llite/dir.c b/drivers/staging/lustre/lustre/llite/dir.c
index e4d3176..70a3ca0 100644
--- a/drivers/staging/lustre/lustre/llite/dir.c
+++ b/drivers/staging/lustre/lustre/llite/dir.c
@@ -498,7 +498,7 @@ int ll_dir_read(struct inode *inode, struct md_op_data *op_data,
 	int		   hash64     = sbi->ll_flags & LL_SBI_64BIT_HASH;
 	struct page	  *page;
 	struct ll_dir_chain   chain;
-	int		   done = 0;
+	bool		   done = false;
 	int		   rc = 0;
 
 	ll_dir_chain_init(&chain);
-- 
1.7.1

[PATCH 14/58] staging: lustre: llite: rename some variables for ll_dir_read

[James Simmons]

From: wang di <di.wang@intel.com>

The variables api32 and hash64 was renamed to is_api32 and
is_hash64.

Signed-off-by: wang di <di.wang@intel.com>
Reviewed-on: http://review.whamcloud.com/7043
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-3531
Reviewed-by: John L. Hammond <john.hammond@intel.com>
Reviewed-by: Jinshan Xiong <jinshan.xiong@intel.com>
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
Signed-off-by: James Simmons <jsimmons@infradead.org>
---
 drivers/staging/lustre/lustre/llite/dir.c |    8 ++++----
 1 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/staging/lustre/lustre/llite/dir.c b/drivers/staging/lustre/lustre/llite/dir.c
index 70a3ca0..907fae4 100644
--- a/drivers/staging/lustre/lustre/llite/dir.c
+++ b/drivers/staging/lustre/lustre/llite/dir.c
@@ -494,8 +494,8 @@ int ll_dir_read(struct inode *inode, struct md_op_data *op_data,
 {
 	struct ll_sb_info    *sbi	= ll_i2sbi(inode);
 	__u64		   pos		= ctx->pos;
-	int		   api32      = ll_need_32bit_api(sbi);
-	int		   hash64     = sbi->ll_flags & LL_SBI_64BIT_HASH;
+	int		   is_api32 = ll_need_32bit_api(sbi);
+	int		   is_hash64 = sbi->ll_flags & LL_SBI_64BIT_HASH;
 	struct page	  *page;
 	struct ll_dir_chain   chain;
 	bool		   done = false;
@@ -545,12 +545,12 @@ int ll_dir_read(struct inode *inode, struct md_op_data *op_data,
 				 */
 				continue;
 
-			if (api32 && hash64)
+			if (is_api32 && is_hash64)
 				lhash = hash >> 32;
 			else
 				lhash = hash;
 			fid_le_to_cpu(&fid, &ent->lde_fid);
-			ino = cl_fid_build_ino(&fid, api32);
+			ino = cl_fid_build_ino(&fid, is_api32);
 			type = ll_dirent_type_get(ent);
 			ctx->pos = lhash;
 			/* For 'll_nfs_get_name_filldir()', it will try
-- 
1.7.1

[PATCH 15/58] staging: lustre: llite: clarify some debug messages for statahead

[James Simmons]

From: wang di <di.wang@intel.com>

Make some of the error reporting more clear for the statahead
thread startup and is_first_dirent() function.

Signed-off-by: wang di <di.wang@intel.com>
Reviewed-on: http://review.whamcloud.com/7043
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-3531
Reviewed-by: John L. Hammond <john.hammond@intel.com>
Reviewed-by: Jinshan Xiong <jinshan.xiong@intel.com>
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
Signed-off-by: James Simmons <jsimmons@infradead.org>
---
 drivers/staging/lustre/lustre/llite/statahead.c |    9 +++++----
 1 files changed, 5 insertions(+), 4 deletions(-)

diff --git a/drivers/staging/lustre/lustre/llite/statahead.c b/drivers/staging/lustre/lustre/llite/statahead.c
index 7a7b11c..fc24a65 100644
--- a/drivers/staging/lustre/lustre/llite/statahead.c
+++ b/drivers/staging/lustre/lustre/llite/statahead.c
@@ -1073,9 +1073,9 @@ static int ll_statahead_thread(void *arg)
 
 		if (IS_ERR(page)) {
 			rc = PTR_ERR(page);
-			CDEBUG(D_READA, "error reading dir "DFID" at %llu/%llu: [rc %d] [parent %u]\n",
+			CDEBUG(D_READA, "error reading dir "DFID" at %llu/%llu: opendir_pid = %u: rc = %d\n",
 			       PFID(ll_inode2fid(dir)), pos, sai->sai_index,
-			       rc, plli->lli_opendir_pid);
+			       plli->lli_opendir_pid, rc);
 			goto out;
 		}
 
@@ -1362,9 +1362,10 @@ static int is_first_dirent(struct inode *dir, struct dentry *dentry)
 			struct ll_inode_info *lli = ll_i2info(dir);
 
 			rc = PTR_ERR(page);
-			CERROR("error reading dir "DFID" at %llu: [rc %d] [parent %u]\n",
+			CERROR("%s: error reading dir "DFID" at %llu: opendir_pid = %u : rc = %d\n",
+			       ll_get_fsname(dir->i_sb, NULL, 0),
 			       PFID(ll_inode2fid(dir)), pos,
-			       rc, lli->lli_opendir_pid);
+			       lli->lli_opendir_pid, rc);
 			break;
 		}
 
-- 
1.7.1

[PATCH 16/58] staging: lustre: llite: remove code never called

[James Simmons]

From: wang di <di.wang@intel.com>

We have if (1) conditionals which is pointless so remove
it and the next code block is never called so remove that
as well.

Signed-off-by: wang di <di.wang@intel.com>
Reviewed-on: http://review.whamcloud.com/7043
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-3531
Reviewed-by: John L. Hammond <john.hammond@intel.com>
Reviewed-by: Jinshan Xiong <jinshan.xiong@intel.com>
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
Signed-off-by: James Simmons <jsimmons@infradead.org>
---
 drivers/staging/lustre/lustre/llite/dir.c       |    9 +--------
 drivers/staging/lustre/lustre/llite/statahead.c |   18 +++---------------
 2 files changed, 4 insertions(+), 23 deletions(-)

diff --git a/drivers/staging/lustre/lustre/llite/dir.c b/drivers/staging/lustre/lustre/llite/dir.c
index 907fae4..2307e70 100644
--- a/drivers/staging/lustre/lustre/llite/dir.c
+++ b/drivers/staging/lustre/lustre/llite/dir.c
@@ -576,7 +576,7 @@ int ll_dir_read(struct inode *inode, struct md_op_data *op_data,
 			 */
 			done = 1;
 			ll_release_page(page, 0);
-		} else if (1 /* chain is exhausted*/) {
+		} else {
 			/*
 			 * Normal case: continue to the next
 			 * page.
@@ -587,13 +587,6 @@ int ll_dir_read(struct inode *inode, struct md_op_data *op_data,
 			next = pos;
 			page = ll_get_dir_page(inode, pos,
 					       &chain);
-		} else {
-			/*
-			 * go into overflow page.
-			 */
-			LASSERT(le32_to_cpu(dp->ldp_flags) &
-				LDF_COLLIDE);
-			ll_release_page(page, 1);
 		}
 	}
 
diff --git a/drivers/staging/lustre/lustre/llite/statahead.c b/drivers/staging/lustre/lustre/llite/statahead.c
index fc24a65..e4ca525 100644
--- a/drivers/staging/lustre/lustre/llite/statahead.c
+++ b/drivers/staging/lustre/lustre/llite/statahead.c
@@ -1222,7 +1222,7 @@ do_it:
 
 			rc = 0;
 			goto out;
-		} else if (1) {
+		} else {
 			/*
 			 * chain is exhausted.
 			 * Normal case: continue to the next page.
@@ -1230,12 +1230,6 @@ do_it:
 			ll_release_page(page, le32_to_cpu(dp->ldp_flags) &
 					      LDF_COLLIDE);
 			page = ll_get_dir_page(dir, pos, &chain);
-		} else {
-			LASSERT(le32_to_cpu(dp->ldp_flags) & LDF_COLLIDE);
-			ll_release_page(page, 1);
-			/*
-			 * go into overflow page.
-			 */
 		}
 	}
 
@@ -1432,8 +1426,8 @@ static int is_first_dirent(struct inode *dir, struct dentry *dentry)
 			 * End of directory reached.
 			 */
 			ll_release_page(page, 0);
-			break;
-		} else if (1) {
+			goto out;
+		} else {
 			/*
 			 * chain is exhausted
 			 * Normal case: continue to the next page.
@@ -1441,12 +1435,6 @@ static int is_first_dirent(struct inode *dir, struct dentry *dentry)
 			ll_release_page(page, le32_to_cpu(dp->ldp_flags) &
 					      LDF_COLLIDE);
 			page = ll_get_dir_page(dir, pos, &chain);
-		} else {
-			/*
-			 * go into overflow page.
-			 */
-			LASSERT(le32_to_cpu(dp->ldp_flags) & LDF_COLLIDE);
-			ll_release_page(page, 1);
 		}
 	}
 
-- 
1.7.1

[PATCH 17/58] staging: lustre: llite: pass in __u64 pos for ll_dir_read

[James Simmons]

From: wang di <di.wang@intel.com>

Some cases we want to preserve the ctx->pos value or use
a different value altogther. So allow the passing in of
a position offset to ll_dir_read.

Signed-off-by: wang di <di.wang@intel.com>
Reviewed-on: http://review.whamcloud.com/10761
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-4906
Reviewed-by: John L. Hammond <john.hammond@intel.com>
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
Signed-off-by: James Simmons <jsimmons@infradead.org>
---
 drivers/staging/lustre/lustre/llite/dir.c          |   19 +++++++++++--------
 .../staging/lustre/lustre/llite/llite_internal.h   |    2 +-
 drivers/staging/lustre/lustre/llite/llite_nfs.c    |    3 ++-
 3 files changed, 14 insertions(+), 10 deletions(-)

diff --git a/drivers/staging/lustre/lustre/llite/dir.c b/drivers/staging/lustre/lustre/llite/dir.c
index 2307e70..031c9e4 100644
--- a/drivers/staging/lustre/lustre/llite/dir.c
+++ b/drivers/staging/lustre/lustre/llite/dir.c
@@ -489,11 +489,11 @@ static __u16 ll_dirent_type_get(struct lu_dirent *ent)
 	return type;
 }
 
-int ll_dir_read(struct inode *inode, struct md_op_data *op_data,
+int ll_dir_read(struct inode *inode, __u64 *ppos, struct md_op_data *op_data,
 		struct dir_context *ctx)
 {
 	struct ll_sb_info    *sbi	= ll_i2sbi(inode);
-	__u64		   pos		= ctx->pos;
+	__u64		   pos		= *ppos;
 	int		   is_api32 = ll_need_32bit_api(sbi);
 	int		   is_hash64 = sbi->ll_flags & LL_SBI_64BIT_HASH;
 	struct page	  *page;
@@ -626,18 +626,21 @@ static int ll_readdir(struct file *filp, struct dir_context *ctx)
 	}
 
 	ctx->pos = pos;
-	rc = ll_dir_read(inode, op_data, ctx);
+	rc = ll_dir_read(inode, &pos, op_data, ctx);
+	pos = ctx->pos;
 	if (lfd)
-		lfd->lfd_pos = ctx->pos;
-	if (ctx->pos == MDS_DIR_END_OFF) {
+		lfd->lfd_pos = pos;
+
+	if (pos == MDS_DIR_END_OFF) {
 		if (api32)
-			ctx->pos = LL_DIR_END_OFF_32BIT;
+			pos = LL_DIR_END_OFF_32BIT;
 		else
-			ctx->pos = LL_DIR_END_OFF;
+			pos = LL_DIR_END_OFF;
 	} else {
 		if (api32 && hash64)
-			ctx->pos >>= 32;
+			pos >>= 32;
 	}
+	ctx->pos = pos;
 	ll_finish_md_op_data(op_data);
 	filp->f_version = inode->i_version;
 
diff --git a/drivers/staging/lustre/lustre/llite/llite_internal.h b/drivers/staging/lustre/lustre/llite/llite_internal.h
index 623455f..e650aeb 100644
--- a/drivers/staging/lustre/lustre/llite/llite_internal.h
+++ b/drivers/staging/lustre/lustre/llite/llite_internal.h
@@ -653,7 +653,7 @@ extern const struct file_operations ll_dir_operations;
 extern const struct inode_operations ll_dir_inode_operations;
 struct page *ll_get_dir_page(struct inode *dir, __u64 hash,
 			     struct ll_dir_chain *chain);
-int ll_dir_read(struct inode *inode, struct md_op_data *op_data,
+int ll_dir_read(struct inode *inode, __u64 *ppos, struct md_op_data *op_data,
 		struct dir_context *ctx);
 
 int ll_get_mdt_idx(struct inode *inode);
diff --git a/drivers/staging/lustre/lustre/llite/llite_nfs.c b/drivers/staging/lustre/lustre/llite/llite_nfs.c
index b74582a..74eb1fc 100644
--- a/drivers/staging/lustre/lustre/llite/llite_nfs.c
+++ b/drivers/staging/lustre/lustre/llite/llite_nfs.c
@@ -256,6 +256,7 @@ static int ll_get_name(struct dentry *dentry, char *name,
 		.ctx.actor = ll_nfs_get_name_filldir,
 	};
 	struct md_op_data *op_data;
+	__u64 pos = 0;
 
 	if (!dir || !S_ISDIR(dir->i_mode)) {
 		rc = -ENOTDIR;
@@ -275,7 +276,7 @@ static int ll_get_name(struct dentry *dentry, char *name,
 	}
 
 	inode_lock(dir);
-	rc = ll_dir_read(dir, op_data, &lgd.ctx);
+	rc = ll_dir_read(dir, &pos, op_data, &lgd.ctx);
 	inode_unlock(dir);
 	ll_finish_md_op_data(op_data);
 	if (!rc && !lgd.lgd_found)
-- 
1.7.1

[PATCH 18/58] staging: lustre: llite: do post work for statahead in readdir case

[James Simmons]

From: wang di <di.wang@intel.com>

Increase the post-work for the statahead thread in the readdir
case since it can become very busy.

Signed-off-by: wang di <di.wang@intel.com>
Reviewed-on: http://review.whamcloud.com/10761
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-4906
Reviewed-by: John L. Hammond <john.hammond@intel.com>
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
Signed-off-by: James Simmons <jsimmons@infradead.org>
---
 .../staging/lustre/lustre/llite/llite_internal.h   |    3 ++-
 drivers/staging/lustre/lustre/llite/statahead.c    |    7 +++++++
 2 files changed, 9 insertions(+), 1 deletions(-)

diff --git a/drivers/staging/lustre/lustre/llite/llite_internal.h b/drivers/staging/lustre/lustre/llite/llite_internal.h
index e650aeb..dc15957 100644
--- a/drivers/staging/lustre/lustre/llite/llite_internal.h
+++ b/drivers/staging/lustre/lustre/llite/llite_internal.h
@@ -997,7 +997,8 @@ struct ll_statahead_info {
 	unsigned int	    sai_ls_all:1,   /* "ls -al", do stat-ahead for
 					     * hidden entries
 					     */
-				sai_agl_valid:1;/* AGL is valid for the dir */
+				sai_agl_valid:1,/* AGL is valid for the dir */
+				sai_in_readpage:1;/* statahead is in readdir() */
 	wait_queue_head_t	sai_waitq;      /* stat-ahead wait queue */
 	struct ptlrpc_thread    sai_thread;     /* stat-ahead thread */
 	struct ptlrpc_thread    sai_agl_thread; /* AGL thread */
diff --git a/drivers/staging/lustre/lustre/llite/statahead.c b/drivers/staging/lustre/lustre/llite/statahead.c
index e4ca525..b5bd107 100644
--- a/drivers/staging/lustre/lustre/llite/statahead.c
+++ b/drivers/staging/lustre/lustre/llite/statahead.c
@@ -1229,7 +1229,9 @@ do_it:
 			 */
 			ll_release_page(page, le32_to_cpu(dp->ldp_flags) &
 					      LDF_COLLIDE);
+			sai->sai_in_readpage = 1;
 			page = ll_get_dir_page(dir, pos, &chain);
+			sai->sai_in_readpage = 0;
 		}
 	}
 
@@ -1548,6 +1550,11 @@ int do_statahead_enter(struct inode *dir, struct dentry **dentryp,
 			return entry ? 1 : -EAGAIN;
 		}
 
+		/* if statahead is busy in readdir, help it do post-work */
+		while (!ll_sa_entry_stated(entry) && sai->sai_in_readpage &&
+		       !sa_received_empty(sai))
+			ll_post_statahead(sai);
+
 		if (!ll_sa_entry_stated(entry)) {
 			sai->sai_index_wait = entry->se_index;
 			lwi = LWI_TIMEOUT_INTR(cfs_time_seconds(30), NULL,
-- 
1.7.1

[PATCH 19/58] staging: lustre: llite: add md_op_data parameter to ll_get_dir_page

[James Simmons]

From: wang di <di.wang@intel.com>

Pass in struct md_op_data for ll_get_dir_page function.

Signed-off-by: wang di <di.wang@intel.com>
Reviewed-on: http://review.whamcloud.com/7043
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-3531
Reviewed-by: John L. Hammond <john.hammond@intel.com>
Reviewed-by: Jinshan Xiong <jinshan.xiong@intel.com>
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
Signed-off-by: James Simmons <jsimmons@infradead.org>
---
 drivers/staging/lustre/lustre/llite/dir.c          |    8 ++++----
 .../staging/lustre/lustre/llite/llite_internal.h   |    4 ++--
 drivers/staging/lustre/lustre/llite/statahead.c    |   15 +++++++++++----
 3 files changed, 17 insertions(+), 10 deletions(-)

diff --git a/drivers/staging/lustre/lustre/llite/dir.c b/drivers/staging/lustre/lustre/llite/dir.c
index 031c9e4..82c7f88 100644
--- a/drivers/staging/lustre/lustre/llite/dir.c
+++ b/drivers/staging/lustre/lustre/llite/dir.c
@@ -322,8 +322,8 @@ static struct page *ll_dir_page_locate(struct inode *dir, __u64 *hash,
 	return page;
 }
 
-struct page *ll_get_dir_page(struct inode *dir, __u64 hash,
-			     struct ll_dir_chain *chain)
+struct page *ll_get_dir_page(struct inode *dir, struct md_op_data *op_data,
+			     __u64 hash, struct ll_dir_chain *chain)
 {
 	ldlm_policy_data_t policy = {.l_inodebits = {MDS_INODELOCK_UPDATE} };
 	struct address_space *mapping = dir->i_mapping;
@@ -503,7 +503,7 @@ int ll_dir_read(struct inode *inode, __u64 *ppos, struct md_op_data *op_data,
 
 	ll_dir_chain_init(&chain);
 
-	page = ll_get_dir_page(inode, pos, &chain);
+	page = ll_get_dir_page(inode, op_data, pos, &chain);
 
 	while (rc == 0 && !done) {
 		struct lu_dirpage *dp;
@@ -585,7 +585,7 @@ int ll_dir_read(struct inode *inode, __u64 *ppos, struct md_op_data *op_data,
 					le32_to_cpu(dp->ldp_flags) &
 					LDF_COLLIDE);
 			next = pos;
-			page = ll_get_dir_page(inode, pos,
+			page = ll_get_dir_page(inode, op_data, pos,
 					       &chain);
 		}
 	}
diff --git a/drivers/staging/lustre/lustre/llite/llite_internal.h b/drivers/staging/lustre/lustre/llite/llite_internal.h
index dc15957..fc0c72c 100644
--- a/drivers/staging/lustre/lustre/llite/llite_internal.h
+++ b/drivers/staging/lustre/lustre/llite/llite_internal.h
@@ -651,8 +651,8 @@ void ll_rw_stats_tally(struct ll_sb_info *sbi, pid_t pid,
 void ll_release_page(struct page *page, int remove);
 extern const struct file_operations ll_dir_operations;
 extern const struct inode_operations ll_dir_inode_operations;
-struct page *ll_get_dir_page(struct inode *dir, __u64 hash,
-			     struct ll_dir_chain *chain);
+struct page *ll_get_dir_page(struct inode *dir, struct md_op_data *op_data,
+			     __u64 hash, struct ll_dir_chain *chain);
 int ll_dir_read(struct inode *inode, __u64 *ppos, struct md_op_data *op_data,
 		struct dir_context *ctx);
 
diff --git a/drivers/staging/lustre/lustre/llite/statahead.c b/drivers/staging/lustre/lustre/llite/statahead.c
index b5bd107..f6c1709 100644
--- a/drivers/staging/lustre/lustre/llite/statahead.c
+++ b/drivers/staging/lustre/lustre/llite/statahead.c
@@ -1065,7 +1065,7 @@ static int ll_statahead_thread(void *arg)
 	wake_up(&thread->t_ctl_waitq);
 
 	ll_dir_chain_init(&chain);
-	page = ll_get_dir_page(dir, pos, &chain);
+	page = ll_get_dir_page(dir, op_data, pos, &chain);
 
 	while (1) {
 		struct lu_dirpage *dp;
@@ -1230,7 +1230,7 @@ do_it:
 			ll_release_page(page, le32_to_cpu(dp->ldp_flags) &
 					      LDF_COLLIDE);
 			sai->sai_in_readpage = 1;
-			page = ll_get_dir_page(dir, pos, &chain);
+			page = ll_get_dir_page(dir, op_data, pos, &chain);
 			sai->sai_in_readpage = 0;
 		}
 	}
@@ -1342,13 +1342,19 @@ static int is_first_dirent(struct inode *dir, struct dentry *dentry)
 {
 	struct ll_dir_chain   chain;
 	struct qstr	  *target = &dentry->d_name;
+	struct md_op_data *op_data;
 	struct page	  *page;
 	__u64		 pos    = 0;
 	int		   dot_de;
 	int		   rc     = LS_NONE_FIRST_DE;
 
+	op_data = ll_prep_md_op_data(NULL, dir, dir, NULL, 0, 0,
+				     LUSTRE_OPC_ANY, dir);
+	if (IS_ERR(op_data))
+		return PTR_ERR(op_data);
+
 	ll_dir_chain_init(&chain);
-	page = ll_get_dir_page(dir, pos, &chain);
+	page = ll_get_dir_page(dir, op_data, pos, &chain);
 
 	while (1) {
 		struct lu_dirpage *dp;
@@ -1436,12 +1442,13 @@ static int is_first_dirent(struct inode *dir, struct dentry *dentry)
 			 */
 			ll_release_page(page, le32_to_cpu(dp->ldp_flags) &
 					      LDF_COLLIDE);
-			page = ll_get_dir_page(dir, pos, &chain);
+			page = ll_get_dir_page(dir, op_data, pos, &chain);
 		}
 	}
 
 out:
 	ll_dir_chain_fini(&chain);
+	ll_finish_md_op_data(op_data);
 	return rc;
 }
 
-- 
1.7.1

[PATCH 20/58] staging: lustre: llite: remove comment from ll_dir_read

[James Simmons]

From: wang di <di.wang@intel.com>

Remove comment about fixing swabbing that is not needed.

Signed-off-by: wang di <di.wang@intel.com>
Reviewed-on: http://review.whamcloud.com/7043
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-3531
Reviewed-by: John L. Hammond <john.hammond@intel.com>
Reviewed-by: Jinshan Xiong <jinshan.xiong@intel.com>
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
Signed-off-by: James Simmons <jsimmons@infradead.org>
---
 drivers/staging/lustre/lustre/llite/dir.c |    4 ----
 1 files changed, 0 insertions(+), 4 deletions(-)

diff --git a/drivers/staging/lustre/lustre/llite/dir.c b/drivers/staging/lustre/lustre/llite/dir.c
index 82c7f88..d854edd 100644
--- a/drivers/staging/lustre/lustre/llite/dir.c
+++ b/drivers/staging/lustre/lustre/llite/dir.c
@@ -526,10 +526,6 @@ int ll_dir_read(struct inode *inode, __u64 *ppos, struct md_op_data *op_data,
 			__u64	  lhash;
 			__u64	  ino;
 
-			/*
-			 * XXX: implement correct swabbing here.
-			 */
-
 			hash = le64_to_cpu(ent->lde_hash);
 			if (hash < pos)
 				/*
-- 
1.7.1

[PATCH 21/58] staging: lustre: llite: style cleanup for llite_internal.h

[James Simmons]

From: wang di <di.wang@intel.com>

Group function prototypes together related to dir.c. Move
ll_release_page to be with function declarations.

Signed-off-by: wang di <di.wang@intel.com>
Reviewed-on: http://review.whamcloud.com/7043
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-3531
Reviewed-by: John L. Hammond <john.hammond@intel.com>
Reviewed-by: Jinshan Xiong <jinshan.xiong@intel.com>
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
Signed-off-by: James Simmons <jsimmons@infradead.org>
---
 .../staging/lustre/lustre/llite/llite_internal.h   |    8 ++++----
 1 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/staging/lustre/lustre/llite/llite_internal.h b/drivers/staging/lustre/lustre/llite/llite_internal.h
index fc0c72c..1ced397 100644
--- a/drivers/staging/lustre/lustre/llite/llite_internal.h
+++ b/drivers/staging/lustre/lustre/llite/llite_internal.h
@@ -648,15 +648,15 @@ void ll_rw_stats_tally(struct ll_sb_info *sbi, pid_t pid,
 		       size_t count, int rw);
 
 /* llite/dir.c */
-void ll_release_page(struct page *page, int remove);
 extern const struct file_operations ll_dir_operations;
 extern const struct inode_operations ll_dir_inode_operations;
-struct page *ll_get_dir_page(struct inode *dir, struct md_op_data *op_data,
-			     __u64 hash, struct ll_dir_chain *chain);
 int ll_dir_read(struct inode *inode, __u64 *ppos, struct md_op_data *op_data,
 		struct dir_context *ctx);
-
 int ll_get_mdt_idx(struct inode *inode);
+struct page *ll_get_dir_page(struct inode *dir, struct md_op_data *op_data,
+			     __u64 hash, struct ll_dir_chain *chain);
+void ll_release_page(struct page *page, int remove);
+
 /* llite/namei.c */
 extern const struct inode_operations ll_special_inode_operations;
 
-- 
1.7.1

[PATCH 22/58] staging: lustre: llite: pass inode to ll_release_page

[James Simmons]

From: wang di <di.wang@intel.com>

Add a inode parameter to ll_release_page. This will be
used in the future.

Signed-off-by: wang di <di.wang@intel.com>
Reviewed-on: http://review.whamcloud.com/7043
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-3531
Reviewed-by: John L. Hammond <john.hammond@intel.com>
Reviewed-by: Jinshan Xiong <jinshan.xiong@intel.com>
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
Signed-off-by: James Simmons <jsimmons@infradead.org>
---
 drivers/staging/lustre/lustre/llite/dir.c          |   17 +++++++++--------
 .../staging/lustre/lustre/llite/llite_internal.h   |    2 +-
 drivers/staging/lustre/lustre/llite/statahead.c    |   20 +++++++++++---------
 3 files changed, 21 insertions(+), 18 deletions(-)

diff --git a/drivers/staging/lustre/lustre/llite/dir.c b/drivers/staging/lustre/lustre/llite/dir.c
index d854edd..3a800b2 100644
--- a/drivers/staging/lustre/lustre/llite/dir.c
+++ b/drivers/staging/lustre/lustre/llite/dir.c
@@ -236,7 +236,7 @@ static int ll_dir_filler(void *_hash, struct page *page0)
 	return rc;
 }
 
-void ll_release_page(struct page *page, int remove)
+void ll_release_page(struct inode *inode, struct page *page, int remove)
 {
 	kunmap(page);
 	if (remove) {
@@ -297,7 +297,7 @@ static struct page *ll_dir_page_locate(struct inode *dir, __u64 *hash,
 			CDEBUG(D_VFSTRACE, "page %lu [%llu %llu], hash %llu\n",
 			       offset, *start, *end, *hash);
 			if (*hash > *end) {
-				ll_release_page(page, 0);
+				ll_release_page(dir, page, 0);
 				page = NULL;
 			} else if (*end != *start && *hash == *end) {
 				/*
@@ -306,8 +306,9 @@ static struct page *ll_dir_page_locate(struct inode *dir, __u64 *hash,
 				 * ll_get_dir_page() will issue RPC to fetch
 				 * the page we want.
 				 */
-				ll_release_page(page,
-				    le32_to_cpu(dp->ldp_flags) & LDF_COLLIDE);
+				ll_release_page(dir, page,
+						le32_to_cpu(dp->ldp_flags) &
+						LDF_COLLIDE);
 				page = NULL;
 			}
 		} else {
@@ -462,7 +463,7 @@ out_unlock:
 	return page;
 
 fail:
-	ll_release_page(page, 1);
+	ll_release_page(dir, page, 1);
 	page = ERR_PTR(-EIO);
 	goto out_unlock;
 }
@@ -560,7 +561,7 @@ int ll_dir_read(struct inode *inode, __u64 *ppos, struct md_op_data *op_data,
 
 		if (done) {
 			pos = hash;
-			ll_release_page(page, 0);
+			ll_release_page(inode, page, 0);
 			break;
 		}
 
@@ -571,13 +572,13 @@ int ll_dir_read(struct inode *inode, __u64 *ppos, struct md_op_data *op_data,
 			 * End of directory reached.
 			 */
 			done = 1;
-			ll_release_page(page, 0);
+			ll_release_page(inode, page, 0);
 		} else {
 			/*
 			 * Normal case: continue to the next
 			 * page.
 			 */
-			ll_release_page(page,
+			ll_release_page(inode, page,
 					le32_to_cpu(dp->ldp_flags) &
 					LDF_COLLIDE);
 			next = pos;
diff --git a/drivers/staging/lustre/lustre/llite/llite_internal.h b/drivers/staging/lustre/lustre/llite/llite_internal.h
index 1ced397..4b03a64 100644
--- a/drivers/staging/lustre/lustre/llite/llite_internal.h
+++ b/drivers/staging/lustre/lustre/llite/llite_internal.h
@@ -655,7 +655,7 @@ int ll_dir_read(struct inode *inode, __u64 *ppos, struct md_op_data *op_data,
 int ll_get_mdt_idx(struct inode *inode);
 struct page *ll_get_dir_page(struct inode *dir, struct md_op_data *op_data,
 			     __u64 hash, struct ll_dir_chain *chain);
-void ll_release_page(struct page *page, int remove);
+void ll_release_page(struct inode *inode, struct page *page, int remove);
 
 /* llite/namei.c */
 extern const struct inode_operations ll_special_inode_operations;
diff --git a/drivers/staging/lustre/lustre/llite/statahead.c b/drivers/staging/lustre/lustre/llite/statahead.c
index f6c1709..1551e7a 100644
--- a/drivers/staging/lustre/lustre/llite/statahead.c
+++ b/drivers/staging/lustre/lustre/llite/statahead.c
@@ -1140,7 +1140,7 @@ interpret_it:
 				ll_post_statahead(sai);
 
 			if (unlikely(!thread_is_running(thread))) {
-				ll_release_page(page, 0);
+				ll_release_page(dir, page, 0);
 				rc = 0;
 				goto out;
 			}
@@ -1164,7 +1164,7 @@ interpret_it:
 
 					if (unlikely(
 						!thread_is_running(thread))) {
-						ll_release_page(page, 0);
+						ll_release_page(dir, page, 0);
 						rc = 0;
 						goto out;
 					}
@@ -1187,7 +1187,7 @@ do_it:
 			/*
 			 * End of directory reached.
 			 */
-			ll_release_page(page, 0);
+			ll_release_page(dir, page, 0);
 			while (1) {
 				l_wait_event(thread->t_ctl_waitq,
 					     !list_empty(&sai->sai_entries_received) ||
@@ -1227,8 +1227,9 @@ do_it:
 			 * chain is exhausted.
 			 * Normal case: continue to the next page.
 			 */
-			ll_release_page(page, le32_to_cpu(dp->ldp_flags) &
-					      LDF_COLLIDE);
+			ll_release_page(dir, page,
+					le32_to_cpu(dp->ldp_flags) &
+					LDF_COLLIDE);
 			sai->sai_in_readpage = 1;
 			page = ll_get_dir_page(dir, op_data, pos, &chain);
 			sai->sai_in_readpage = 0;
@@ -1425,7 +1426,7 @@ static int is_first_dirent(struct inode *dir, struct dentry *dentry)
 			else
 				rc = LS_FIRST_DOT_DE;
 
-			ll_release_page(page, 0);
+			ll_release_page(dir, page, 0);
 			goto out;
 		}
 		pos = le64_to_cpu(dp->ldp_hash_end);
@@ -1433,15 +1434,16 @@ static int is_first_dirent(struct inode *dir, struct dentry *dentry)
 			/*
 			 * End of directory reached.
 			 */
-			ll_release_page(page, 0);
+			ll_release_page(dir, page, 0);
 			goto out;
 		} else {
 			/*
 			 * chain is exhausted
 			 * Normal case: continue to the next page.
 			 */
-			ll_release_page(page, le32_to_cpu(dp->ldp_flags) &
-					      LDF_COLLIDE);
+			ll_release_page(dir, page,
+					le32_to_cpu(dp->ldp_flags) &
+					LDF_COLLIDE);
 			page = ll_get_dir_page(dir, op_data, pos, &chain);
 		}
 	}
-- 
1.7.1

[PATCH 23/58] staging: lustre: llite: change remove parameter to bool

[James Simmons]

From: wang di <di.wang@intel.com>

Change the 3rd parameter remove to a bool for ll_release_page
function.

Signed-off-by: wang di <di.wang@intel.com>
Reviewed-on: http://review.whamcloud.com/7043
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-3531
Reviewed-by: John L. Hammond <john.hammond@intel.com>
Reviewed-by: Jinshan Xiong <jinshan.xiong@intel.com>
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
Signed-off-by: James Simmons <jsimmons@infradead.org>
---
 drivers/staging/lustre/lustre/llite/dir.c          |   10 +++++-----
 .../staging/lustre/lustre/llite/llite_internal.h   |    2 +-
 drivers/staging/lustre/lustre/llite/statahead.c    |   10 +++++-----
 3 files changed, 11 insertions(+), 11 deletions(-)

diff --git a/drivers/staging/lustre/lustre/llite/dir.c b/drivers/staging/lustre/lustre/llite/dir.c
index 3a800b2..a72b486 100644
--- a/drivers/staging/lustre/lustre/llite/dir.c
+++ b/drivers/staging/lustre/lustre/llite/dir.c
@@ -236,7 +236,7 @@ static int ll_dir_filler(void *_hash, struct page *page0)
 	return rc;
 }
 
-void ll_release_page(struct inode *inode, struct page *page, int remove)
+void ll_release_page(struct inode *inode, struct page *page, bool remove)
 {
 	kunmap(page);
 	if (remove) {
@@ -297,7 +297,7 @@ static struct page *ll_dir_page_locate(struct inode *dir, __u64 *hash,
 			CDEBUG(D_VFSTRACE, "page %lu [%llu %llu], hash %llu\n",
 			       offset, *start, *end, *hash);
 			if (*hash > *end) {
-				ll_release_page(dir, page, 0);
+				ll_release_page(dir, page, false);
 				page = NULL;
 			} else if (*end != *start && *hash == *end) {
 				/*
@@ -463,7 +463,7 @@ out_unlock:
 	return page;
 
 fail:
-	ll_release_page(dir, page, 1);
+	ll_release_page(dir, page, true);
 	page = ERR_PTR(-EIO);
 	goto out_unlock;
 }
@@ -561,7 +561,7 @@ int ll_dir_read(struct inode *inode, __u64 *ppos, struct md_op_data *op_data,
 
 		if (done) {
 			pos = hash;
-			ll_release_page(inode, page, 0);
+			ll_release_page(inode, page, false);
 			break;
 		}
 
@@ -572,7 +572,7 @@ int ll_dir_read(struct inode *inode, __u64 *ppos, struct md_op_data *op_data,
 			 * End of directory reached.
 			 */
 			done = 1;
-			ll_release_page(inode, page, 0);
+			ll_release_page(inode, page, false);
 		} else {
 			/*
 			 * Normal case: continue to the next
diff --git a/drivers/staging/lustre/lustre/llite/llite_internal.h b/drivers/staging/lustre/lustre/llite/llite_internal.h
index 4b03a64..07b6918 100644
--- a/drivers/staging/lustre/lustre/llite/llite_internal.h
+++ b/drivers/staging/lustre/lustre/llite/llite_internal.h
@@ -655,7 +655,7 @@ int ll_dir_read(struct inode *inode, __u64 *ppos, struct md_op_data *op_data,
 int ll_get_mdt_idx(struct inode *inode);
 struct page *ll_get_dir_page(struct inode *dir, struct md_op_data *op_data,
 			     __u64 hash, struct ll_dir_chain *chain);
-void ll_release_page(struct inode *inode, struct page *page, int remove);
+void ll_release_page(struct inode *inode, struct page *page, bool remove);
 
 /* llite/namei.c */
 extern const struct inode_operations ll_special_inode_operations;
diff --git a/drivers/staging/lustre/lustre/llite/statahead.c b/drivers/staging/lustre/lustre/llite/statahead.c
index 1551e7a..7b23497 100644
--- a/drivers/staging/lustre/lustre/llite/statahead.c
+++ b/drivers/staging/lustre/lustre/llite/statahead.c
@@ -1140,7 +1140,7 @@ interpret_it:
 				ll_post_statahead(sai);
 
 			if (unlikely(!thread_is_running(thread))) {
-				ll_release_page(dir, page, 0);
+				ll_release_page(dir, page, false);
 				rc = 0;
 				goto out;
 			}
@@ -1164,7 +1164,7 @@ interpret_it:
 
 					if (unlikely(
 						!thread_is_running(thread))) {
-						ll_release_page(dir, page, 0);
+						ll_release_page(dir, page, false);
 						rc = 0;
 						goto out;
 					}
@@ -1187,7 +1187,7 @@ do_it:
 			/*
 			 * End of directory reached.
 			 */
-			ll_release_page(dir, page, 0);
+			ll_release_page(dir, page, false);
 			while (1) {
 				l_wait_event(thread->t_ctl_waitq,
 					     !list_empty(&sai->sai_entries_received) ||
@@ -1426,7 +1426,7 @@ static int is_first_dirent(struct inode *dir, struct dentry *dentry)
 			else
 				rc = LS_FIRST_DOT_DE;
 
-			ll_release_page(dir, page, 0);
+			ll_release_page(dir, page, false);
 			goto out;
 		}
 		pos = le64_to_cpu(dp->ldp_hash_end);
@@ -1434,7 +1434,7 @@ static int is_first_dirent(struct inode *dir, struct dentry *dentry)
 			/*
 			 * End of directory reached.
 			 */
-			ll_release_page(dir, page, 0);
+			ll_release_page(dir, page, false);
 			goto out;
 		} else {
 			/*
-- 
1.7.1

[PATCH 24/58] staging: lustre: mdc: don't take rpc lock for readdir case

[James Simmons]

From: wang di <di.wang@intel.com>

If the operation is IT_READDIR don't need to handle the
mdc RPC lock.

Signed-off-by: wang di <di.wang@intel.com>
Reviewed-on: http://review.whamcloud.com/10761
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-4906
Reviewed-by: John L. Hammond <john.hammond@intel.com>
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
Signed-off-by: James Simmons <jsimmons@infradead.org>
---
 drivers/staging/lustre/lustre/include/lustre_mdc.h |    4 ++--
 1 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/staging/lustre/lustre/include/lustre_mdc.h b/drivers/staging/lustre/lustre/include/lustre_mdc.h
index fa62b95..0a8c639 100644
--- a/drivers/staging/lustre/lustre/include/lustre_mdc.h
+++ b/drivers/staging/lustre/lustre/include/lustre_mdc.h
@@ -96,7 +96,7 @@ static inline void mdc_get_rpc_lock(struct mdc_rpc_lock *lck,
 				    struct lookup_intent *it)
 {
 	if (it && (it->it_op == IT_GETATTR || it->it_op == IT_LOOKUP ||
-		   it->it_op == IT_LAYOUT))
+		   it->it_op == IT_LAYOUT || it->it_op == IT_READDIR))
 		return;
 
 	/* This would normally block until the existing request finishes.
@@ -136,7 +136,7 @@ static inline void mdc_put_rpc_lock(struct mdc_rpc_lock *lck,
 				    struct lookup_intent *it)
 {
 	if (it && (it->it_op == IT_GETATTR || it->it_op == IT_LOOKUP ||
-		   it->it_op == IT_LAYOUT))
+		   it->it_op == IT_LAYOUT || it->it_op == IT_READDIR))
 		return;
 
 	if (lck->rpcl_it == MDC_FAKE_RPCL_IT) { /* OBD_FAIL_MDC_RPCS_SEM */
-- 
1.7.1

[PATCH 25/58] staging: lustre: lmv: remove unused lmv_get_mea function

[James Simmons]

From: wang di <di.wang@intel.com>

The function lmv_get_mea() is not used so remove it.

Signed-off-by: wang di <di.wang@intel.com>
Reviewed-on: http://review.whamcloud.com/7043
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-3531
Reviewed-by: John L. Hammond <john.hammond@intel.com>
Reviewed-by: Jinshan Xiong <jinshan.xiong@intel.com>
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
Signed-off-by: James Simmons <jsimmons@infradead.org>
---
 drivers/staging/lustre/lustre/lmv/lmv_internal.h |   24 ----------------------
 1 files changed, 0 insertions(+), 24 deletions(-)

diff --git a/drivers/staging/lustre/lustre/lmv/lmv_internal.h b/drivers/staging/lustre/lustre/lmv/lmv_internal.h
index 471470b..ab01560 100644
--- a/drivers/staging/lustre/lustre/lmv/lmv_internal.h
+++ b/drivers/staging/lustre/lustre/lmv/lmv_internal.h
@@ -55,30 +55,6 @@ int __lmv_fid_alloc(struct lmv_obd *lmv, struct lu_fid *fid, u32 mds);
 int lmv_fid_alloc(struct obd_export *exp, struct lu_fid *fid,
 		  struct md_op_data *op_data);
 
-static inline struct lmv_stripe_md *lmv_get_mea(struct ptlrpc_request *req)
-{
-	struct mdt_body	 *body;
-	struct lmv_stripe_md    *mea;
-
-	LASSERT(req);
-
-	body = req_capsule_server_get(&req->rq_pill, &RMF_MDT_BODY);
-
-	if (!body || !S_ISDIR(body->mode) || !body->eadatasize)
-		return NULL;
-
-	mea = req_capsule_server_sized_get(&req->rq_pill, &RMF_MDT_MD,
-					   body->eadatasize);
-	if (mea->mea_count == 0)
-		return NULL;
-	if (mea->mea_magic != MEA_MAGIC_LAST_CHAR &&
-	    mea->mea_magic != MEA_MAGIC_ALL_CHARS &&
-	    mea->mea_magic != MEA_MAGIC_HASH_SEGMENT)
-		return NULL;
-
-	return mea;
-}
-
 static inline int lmv_get_easize(struct lmv_obd *lmv)
 {
 	return sizeof(struct lmv_stripe_md) +
-- 
1.7.1

[PATCH 26/58] staging: lustre: lmv: remove duplicate MAX_HASH_*

[James Simmons]

From: wang di <di.wang@intel.com>

The MAX_HASH_* macros already exist in obd.h. Remove
the duplicated defines in lustre_idl.h.

Signed-off-by: wang di <di.wang@intel.com>
Reviewed-on: http://review.whamcloud.com/7043
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-3531
Reviewed-by: John L. Hammond <john.hammond@intel.com>
Reviewed-by: Jinshan Xiong <jinshan.xiong@intel.com>
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
Signed-off-by: James Simmons <jsimmons@infradead.org>
---
 .../lustre/lustre/include/lustre/lustre_idl.h      |    4 ----
 1 files changed, 0 insertions(+), 4 deletions(-)

diff --git a/drivers/staging/lustre/lustre/include/lustre/lustre_idl.h b/drivers/staging/lustre/lustre/include/lustre/lustre_idl.h
index 32471a6..5f31724 100644
--- a/drivers/staging/lustre/lustre/include/lustre/lustre_idl.h
+++ b/drivers/staging/lustre/lustre/include/lustre/lustre_idl.h
@@ -2486,10 +2486,6 @@ struct lmv_desc {
 #define MEA_MAGIC_ALL_CHARS      0xb222a11c
 #define MEA_MAGIC_HASH_SEGMENT   0xb222a11b
 
-#define MAX_HASH_SIZE_32	 0x7fffffffUL
-#define MAX_HASH_SIZE	    0x7fffffffffffffffULL
-#define MAX_HASH_HIGHEST_BIT     0x1000000000000000ULL
-
 /* lmv structures */
 #define LMV_MAGIC_V1	0x0CD10CD0	/* normal stripe lmv magic */
 #define LMV_USER_MAGIC	0x0CD20CD0	/* default lmv magic*/
-- 
1.7.1

[PATCH 27/58] staging: lustre: lmv: change handling of lmv striping information

[James Simmons]

From: wang di <di.wang@intel.com>

The lmv_[un]pack_md function are used to calculate the
size of the data used to represent the LMV striping data.
The original code was straight forward in its calculate
with lmv_get_easize since only one type of data format
could exist. We want to be able to support different
version of this data in the future so this patch moves
to generating the size of the data using the stripe count
and which LMV_MAGIC_* version.

Signed-off-by: wang di <di.wang@intel.com>
Reviewed-on: http://review.whamcloud.com/7043
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-3531
Reviewed-by: John L. Hammond <john.hammond@intel.com>
Reviewed-by: Jinshan Xiong <jinshan.xiong@intel.com>
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
Signed-off-by: James Simmons <jsimmons@infradead.org>
---
 .../lustre/lustre/include/lustre/lustre_idl.h      |    4 -
 drivers/staging/lustre/lustre/include/lustre_lmv.h |   15 +-
 drivers/staging/lustre/lustre/lmv/lmv_internal.h   |    7 +
 drivers/staging/lustre/lustre/lmv/lmv_obd.c        |  245 +++++++++++++++-----
 4 files changed, 198 insertions(+), 73 deletions(-)

diff --git a/drivers/staging/lustre/lustre/include/lustre/lustre_idl.h b/drivers/staging/lustre/lustre/include/lustre/lustre_idl.h
index 5f31724..0ad6605 100644
--- a/drivers/staging/lustre/lustre/include/lustre/lustre_idl.h
+++ b/drivers/staging/lustre/lustre/include/lustre/lustre_idl.h
@@ -2482,10 +2482,6 @@ struct lmv_desc {
 	struct obd_uuid ld_uuid;
 };
 
-#define MEA_MAGIC_LAST_CHAR      0xb2221ca1
-#define MEA_MAGIC_ALL_CHARS      0xb222a11c
-#define MEA_MAGIC_HASH_SEGMENT   0xb222a11b
-
 /* lmv structures */
 #define LMV_MAGIC_V1	0x0CD10CD0	/* normal stripe lmv magic */
 #define LMV_USER_MAGIC	0x0CD20CD0	/* default lmv magic*/
diff --git a/drivers/staging/lustre/lustre/include/lustre_lmv.h b/drivers/staging/lustre/lustre/include/lustre_lmv.h
index 0620c8c..784d67b 100644
--- a/drivers/staging/lustre/lustre/include/lustre_lmv.h
+++ b/drivers/staging/lustre/lustre/include/lustre_lmv.h
@@ -41,12 +41,15 @@ struct lmv_oinfo {
 };
 
 struct lmv_stripe_md {
-	__u32	mea_magic;
-	__u32	mea_count;
-	__u32	mea_master;
-	__u32	mea_padding;
-	char	mea_pool_name[LOV_MAXPOOLNAME];
-	struct lu_fid mea_ids[0];
+	__u32	lsm_md_magic;
+	__u32	lsm_md_stripe_count;
+	__u32	lsm_md_master_mdt_index;
+	__u32	lsm_md_hash_type;
+	__u32	lsm_md_layout_version;
+	__u32	lsm_md_default_count;
+	__u32	lsm_md_default_index;
+	char	lsm_md_pool_name[LOV_MAXPOOLNAME];
+	struct lmv_oinfo lsm_md_oinfo[0];
 };
 
 union lmv_mds_md;
diff --git a/drivers/staging/lustre/lustre/lmv/lmv_internal.h b/drivers/staging/lustre/lustre/lmv/lmv_internal.h
index ab01560..90a9786 100644
--- a/drivers/staging/lustre/lustre/lmv/lmv_internal.h
+++ b/drivers/staging/lustre/lustre/lmv/lmv_internal.h
@@ -94,6 +94,13 @@ lmv_find_target(struct lmv_obd *lmv, const struct lu_fid *fid)
 	return lmv_get_target(lmv, mds);
 }
 
+static inline int lmv_stripe_md_size(int stripe_count)
+{
+	struct lmv_stripe_md *lsm;
+
+	return sizeof(*lsm) + stripe_count * sizeof(lsm->lsm_md_oinfo[0]);
+}
+
 struct lmv_tgt_desc
 *lmv_locate_mds(struct lmv_obd *lmv, struct md_op_data *op_data,
 		struct lu_fid *fid);
diff --git a/drivers/staging/lustre/lustre/lmv/lmv_obd.c b/drivers/staging/lustre/lustre/lmv/lmv_obd.c
index 8e83263..1ba5900 100644
--- a/drivers/staging/lustre/lustre/lmv/lmv_obd.c
+++ b/drivers/staging/lustre/lustre/lmv/lmv_obd.c
@@ -2376,105 +2376,224 @@ static int lmv_set_info_async(const struct lu_env *env, struct obd_export *exp,
 	return -EINVAL;
 }
 
-static int lmv_packmd(struct obd_export *exp, struct lov_mds_md **lmmp,
-		      struct lov_stripe_md *lsm)
+static int lmv_pack_md_v1(const struct lmv_stripe_md *lsm,
+			  struct lmv_mds_md_v1 *lmm1)
 {
-	struct obd_device	 *obd = class_exp2obd(exp);
-	struct lmv_obd	    *lmv = &obd->u.lmv;
-	struct lmv_stripe_md      *meap;
-	struct lmv_stripe_md      *lsmp;
-	int			mea_size;
-	int			i;
+	int cplen;
+	int i;
+
+	lmm1->lmv_magic = cpu_to_le32(lsm->lsm_md_magic);
+	lmm1->lmv_stripe_count = cpu_to_le32(lsm->lsm_md_stripe_count);
+	lmm1->lmv_master_mdt_index = cpu_to_le32(lsm->lsm_md_master_mdt_index);
+	lmm1->lmv_hash_type = cpu_to_le32(lsm->lsm_md_hash_type);
+	cplen = strlcpy(lmm1->lmv_pool_name, lsm->lsm_md_pool_name,
+			sizeof(lmm1->lmv_pool_name));
+	if (cplen >= sizeof(lmm1->lmv_pool_name))
+		return -E2BIG;
+
+	for (i = 0; i < lsm->lsm_md_stripe_count; i++)
+		fid_cpu_to_le(&lmm1->lmv_stripe_fids[i],
+			      &lsm->lsm_md_oinfo[i].lmo_fid);
+	return 0;
+}
+
+int lmv_pack_md(union lmv_mds_md **lmmp, const struct lmv_stripe_md *lsm,
+		int stripe_count)
+{
+	int lmm_size = 0, rc = 0;
+	bool allocated = false;
 
-	mea_size = lmv_get_easize(lmv);
-	if (!lmmp)
-		return mea_size;
+	LASSERT(lmmp);
 
+	/* Free lmm */
 	if (*lmmp && !lsm) {
+		int stripe_cnt;
+
+		stripe_cnt = lmv_mds_md_stripe_count_get(*lmmp);
+		lmm_size = lmv_mds_md_size(stripe_cnt,
+					   le32_to_cpu((*lmmp)->lmv_magic));
+		if (!lmm_size)
+			return -EINVAL;
 		kvfree(*lmmp);
 		*lmmp = NULL;
 		return 0;
 	}
 
+	/* Alloc lmm */
+	if (!*lmmp && !lsm) {
+		lmm_size = lmv_mds_md_size(stripe_count, LMV_MAGIC);
+		LASSERT(lmm_size > 0);
+		*lmmp = libcfs_kvzalloc(lmm_size, GFP_NOFS);
+		if (!*lmmp)
+			return -ENOMEM;
+		lmv_mds_md_stripe_count_set(*lmmp, stripe_count);
+		(*lmmp)->lmv_magic = cpu_to_le32(LMV_MAGIC);
+		return lmm_size;
+	}
+
+	/* pack lmm */
+	LASSERT(lsm);
+	lmm_size = lmv_mds_md_size(lsm->lsm_md_stripe_count,
+				   lsm->lsm_md_magic);
 	if (!*lmmp) {
-		*lmmp = libcfs_kvzalloc(mea_size, GFP_NOFS);
+		*lmmp = libcfs_kvzalloc(lmm_size, GFP_NOFS);
 		if (!*lmmp)
 			return -ENOMEM;
+		allocated = true;
 	}
 
-	if (!lsm)
-		return mea_size;
+	switch (lsm->lsm_md_magic) {
+	case LMV_MAGIC_V1:
+		rc = lmv_pack_md_v1(lsm, &(*lmmp)->lmv_md_v1);
+		break;
+	default:
+		rc = -EINVAL;
+		break;
+	}
 
-	lsmp = (struct lmv_stripe_md *)lsm;
-	meap = (struct lmv_stripe_md *)*lmmp;
+	if (rc && allocated) {
+		kvfree(*lmmp);
+		*lmmp = NULL;
+	}
 
-	if (lsmp->mea_magic != MEA_MAGIC_LAST_CHAR &&
-	    lsmp->mea_magic != MEA_MAGIC_ALL_CHARS)
-		return -EINVAL;
+	return lmm_size;
+}
+EXPORT_SYMBOL(lmv_pack_md);
 
-	meap->mea_magic = cpu_to_le32(lsmp->mea_magic);
-	meap->mea_count = cpu_to_le32(lsmp->mea_count);
-	meap->mea_master = cpu_to_le32(lsmp->mea_master);
+static int lmv_unpack_md_v1(struct obd_export *exp, struct lmv_stripe_md *lsm,
+			    const struct lmv_mds_md_v1 *lmm1)
+{
+	struct lmv_obd *lmv = &exp->exp_obd->u.lmv;
+	int stripe_count;
+	int rc = 0;
+	int cplen;
+	int i;
 
-	for (i = 0; i < lmv->desc.ld_tgt_count; i++) {
-		meap->mea_ids[i] = lsmp->mea_ids[i];
-		fid_cpu_to_le(&meap->mea_ids[i], &lsmp->mea_ids[i]);
+	lsm->lsm_md_magic = le32_to_cpu(lmm1->lmv_magic);
+	lsm->lsm_md_stripe_count = le32_to_cpu(lmm1->lmv_stripe_count);
+	lsm->lsm_md_master_mdt_index = le32_to_cpu(lmm1->lmv_master_mdt_index);
+	lsm->lsm_md_hash_type = le32_to_cpu(lmm1->lmv_hash_type);
+	lsm->lsm_md_layout_version = le32_to_cpu(lmm1->lmv_layout_version);
+	cplen = strlcpy(lsm->lsm_md_pool_name, lmm1->lmv_pool_name,
+			sizeof(lsm->lsm_md_pool_name));
+
+	if (cplen >= sizeof(lsm->lsm_md_pool_name))
+		return -E2BIG;
+
+	CDEBUG(D_INFO, "unpack lsm count %d, master %d hash_type %d layout_version %d\n",
+	       lsm->lsm_md_stripe_count, lsm->lsm_md_master_mdt_index,
+	       lsm->lsm_md_hash_type, lsm->lsm_md_layout_version);
+
+	stripe_count = le32_to_cpu(lmm1->lmv_stripe_count);
+	for (i = 0; i < le32_to_cpu(stripe_count); i++) {
+		fid_le_to_cpu(&lsm->lsm_md_oinfo[i].lmo_fid,
+			      &lmm1->lmv_stripe_fids[i]);
+		rc = lmv_fld_lookup(lmv, &lsm->lsm_md_oinfo[i].lmo_fid,
+				    &lsm->lsm_md_oinfo[i].lmo_mds);
+		if (rc)
+			return rc;
+		CDEBUG(D_INFO, "unpack fid #%d "DFID"\n", i,
+		       PFID(&lsm->lsm_md_oinfo[i].lmo_fid));
 	}
 
-	return mea_size;
+	return rc;
 }
 
-static int lmv_unpackmd(struct obd_export *exp, struct lov_stripe_md **lsmp,
-			struct lov_mds_md *lmm, int lmm_size)
+int lmv_unpack_md(struct obd_export *exp, struct lmv_stripe_md **lsmp,
+		  const union lmv_mds_md *lmm, int stripe_count)
 {
-	struct obd_device	  *obd = class_exp2obd(exp);
-	struct lmv_stripe_md      **tmea = (struct lmv_stripe_md **)lsmp;
-	struct lmv_stripe_md       *mea = (struct lmv_stripe_md *)lmm;
-	struct lmv_obd	     *lmv = &obd->u.lmv;
-	int			 mea_size;
-	int			 i;
-	__u32		       magic;
+	struct lmv_stripe_md *lsm;
+	bool allocated = false;
+	int lsm_size, rc;
+
+	LASSERT(lsmp);
+
+	lsm = *lsmp;
+	/* Free memmd */
+	if (lsm && !lmm) {
+		int i;
 
-	mea_size = lmv_get_easize(lmv);
-	if (!lsmp)
-		return mea_size;
+		for (i = 1; i < lsm->lsm_md_stripe_count; i++) {
+			if (lsm->lsm_md_oinfo[i].lmo_root)
+				iput(lsm->lsm_md_oinfo[i].lmo_root);
+		}
 
-	if (*lsmp && !lmm) {
-		kvfree(*tmea);
+		kvfree(lsm);
 		*lsmp = NULL;
 		return 0;
 	}
 
-	LASSERT(mea_size == lmm_size);
+	/* Alloc memmd */
+	if (!lsm && !lmm) {
+		lsm_size = lmv_stripe_md_size(stripe_count);
+		lsm = libcfs_kvzalloc(lsm_size, GFP_NOFS);
+		if (!lsm)
+			return -ENOMEM;
+		lsm->lsm_md_stripe_count = stripe_count;
+		*lsmp = lsm;
+		return 0;
+	}
 
-	*tmea = libcfs_kvzalloc(mea_size, GFP_NOFS);
-	if (!*tmea)
-		return -ENOMEM;
+	/* Unpack memmd */
+	if (le32_to_cpu(lmm->lmv_magic) != LMV_MAGIC_V1) {
+		CERROR("%s: invalid magic %x.\n", exp->exp_obd->obd_name,
+		       le32_to_cpu(lmm->lmv_magic));
+		return -EINVAL;
+	}
 
-	if (!lmm)
-		return mea_size;
+	lsm_size = lmv_stripe_md_size(lmv_mds_md_stripe_count_get(lmm));
+	if (!lsm) {
+		lsm = libcfs_kvzalloc(lsm_size, GFP_NOFS);
+		if (!lsm)
+			return -ENOMEM;
+		allocated = true;
+		*lsmp = lsm;
+	}
 
-	if (mea->mea_magic == MEA_MAGIC_LAST_CHAR ||
-	    mea->mea_magic == MEA_MAGIC_ALL_CHARS ||
-	    mea->mea_magic == MEA_MAGIC_HASH_SEGMENT) {
-		magic = le32_to_cpu(mea->mea_magic);
-	} else {
-		/*
-		 * Old mea is not handled here.
-		 */
-		CERROR("Old not supportable EA is found\n");
-		LBUG();
+	switch (le32_to_cpu(lmm->lmv_magic)) {
+	case LMV_MAGIC_V1:
+		rc = lmv_unpack_md_v1(exp, lsm, &lmm->lmv_md_v1);
+		break;
+	default:
+		CERROR("%s: unrecognized magic %x\n", exp->exp_obd->obd_name,
+		       le32_to_cpu(lmm->lmv_magic));
+		rc = -EINVAL;
+		break;
 	}
 
-	(*tmea)->mea_magic = magic;
-	(*tmea)->mea_count = le32_to_cpu(mea->mea_count);
-	(*tmea)->mea_master = le32_to_cpu(mea->mea_master);
+	if (rc && allocated) {
+		kvfree(lsm);
+		*lsmp = NULL;
+		lsm_size = rc;
+	}
+	return lsm_size;
+}
 
-	for (i = 0; i < (*tmea)->mea_count; i++) {
-		(*tmea)->mea_ids[i] = mea->mea_ids[i];
-		fid_le_to_cpu(&(*tmea)->mea_ids[i], &(*tmea)->mea_ids[i]);
+int lmv_unpackmd(struct obd_export *exp, struct lov_stripe_md **lsmp,
+		 struct lov_mds_md *lmm, int disk_len)
+{
+	return lmv_unpack_md(exp, (struct lmv_stripe_md **)lsmp,
+			     (union lmv_mds_md *)lmm, disk_len);
+}
+
+int lmv_packmd(struct obd_export *exp, struct lov_mds_md **lmmp,
+	       struct lov_stripe_md *lsm)
+{
+	const struct lmv_stripe_md *lmv = (struct lmv_stripe_md *)lsm;
+	struct obd_device *obd = exp->exp_obd;
+	struct lmv_obd *lmv_obd = &obd->u.lmv;
+	int stripe_count;
+
+	if (!lmmp) {
+		if (lsm)
+			stripe_count = lmv->lsm_md_stripe_count;
+		else
+			stripe_count = lmv_obd->desc.ld_tgt_count;
+
+		return lmv_mds_md_size(stripe_count, LMV_MAGIC_V1);
 	}
-	return mea_size;
+
+	return lmv_pack_md((union lmv_mds_md **)lmmp, lmv, 0);
 }
 
 static int lmv_cancel_unused(struct obd_export *exp, const struct lu_fid *fid,
-- 
1.7.1

[PATCH 28/58] staging: lustre: lmv: remove lmv_get_easize

[James Simmons]

From: wang di <di.wang@intel.com>

Completely replace lmv_get_easize with lmv_mds_md_size.
With this change we can delete lmv_get_easize.

Signed-off-by: wang di <di.wang@intel.com>
Reviewed-on: http://review.whamcloud.com/7043
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-3531
Reviewed-by: John L. Hammond <john.hammond@intel.com>
Reviewed-by: Jinshan Xiong <jinshan.xiong@intel.com>
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
Signed-off-by: James Simmons <jsimmons@infradead.org>
---
 drivers/staging/lustre/lustre/lmv/lmv_internal.h |    7 -------
 drivers/staging/lustre/lustre/lmv/lmv_obd.c      |    2 +-
 2 files changed, 1 insertions(+), 8 deletions(-)

diff --git a/drivers/staging/lustre/lustre/lmv/lmv_internal.h b/drivers/staging/lustre/lustre/lmv/lmv_internal.h
index 90a9786..f4c917b 100644
--- a/drivers/staging/lustre/lustre/lmv/lmv_internal.h
+++ b/drivers/staging/lustre/lustre/lmv/lmv_internal.h
@@ -55,13 +55,6 @@ int __lmv_fid_alloc(struct lmv_obd *lmv, struct lu_fid *fid, u32 mds);
 int lmv_fid_alloc(struct obd_export *exp, struct lu_fid *fid,
 		  struct md_op_data *op_data);
 
-static inline int lmv_get_easize(struct lmv_obd *lmv)
-{
-	return sizeof(struct lmv_stripe_md) +
-		lmv->desc.ld_tgt_count *
-		sizeof(struct lu_fid);
-}
-
 static inline struct lmv_tgt_desc *
 lmv_get_target(struct lmv_obd *lmv, u32 mds)
 {
diff --git a/drivers/staging/lustre/lustre/lmv/lmv_obd.c b/drivers/staging/lustre/lustre/lmv/lmv_obd.c
index 1ba5900..0b1260d 100644
--- a/drivers/staging/lustre/lustre/lmv/lmv_obd.c
+++ b/drivers/staging/lustre/lustre/lmv/lmv_obd.c
@@ -558,7 +558,7 @@ int lmv_check_connect(struct obd_device *obd)
 	lmv_set_timeouts(obd);
 	class_export_put(lmv->exp);
 	lmv->connected = 1;
-	easize = lmv_get_easize(lmv);
+	easize = lmv_mds_md_size(lmv->desc.ld_tgt_count, LMV_MAGIC);
 	lmv_init_ea_size(obd->obd_self_export, easize, 0, 0, 0);
 	mutex_unlock(&lmv->lmv_init_mutex);
 	return 0;
-- 
1.7.1

[PATCH 29/58] staging: lustre: lmv: replace obd_free_memmd with lmv_free_memmd

[James Simmons]

From: wang di <di.wang@intel.com>

Use lmv_free_memmd for proper cleanup instead of
the generic obd_free_memmd.

Signed-off-by: wang di <di.wang@intel.com>
Reviewed-on: http://review.whamcloud.com/7043
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-3531
Reviewed-by: John L. Hammond <john.hammond@intel.com>
Reviewed-by: Jinshan Xiong <jinshan.xiong@intel.com>
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
Signed-off-by: James Simmons <jsimmons@infradead.org>
---
 drivers/staging/lustre/lustre/lmv/lmv_obd.c |    2 +-
 1 files changed, 1 insertions(+), 1 deletions(-)

diff --git a/drivers/staging/lustre/lustre/lmv/lmv_obd.c b/drivers/staging/lustre/lustre/lmv/lmv_obd.c
index 0b1260d..6be2afc 100644
--- a/drivers/staging/lustre/lustre/lmv/lmv_obd.c
+++ b/drivers/staging/lustre/lustre/lmv/lmv_obd.c
@@ -2692,7 +2692,7 @@ static int lmv_free_lustre_md(struct obd_export *exp, struct lustre_md *md)
 	struct lmv_tgt_desc *tgt = lmv->tgts[0];
 
 	if (md->lmv)
-		obd_free_memmd(exp, (void *)&md->lmv);
+		lmv_free_memmd(md->lmv);
 	if (!tgt || !tgt->ltd_exp)
 		return -EINVAL;
 	return md_free_lustre_md(tgt->ltd_exp, md);
-- 
1.7.1

[PATCH 30/58] staging: lustre: create striped directory

[James Simmons]

[-- Warning: decoded text below may be mangled, UTF-8 assumed --]
[-- Attachment #1: Type: text/plain, Size: 49039 bytes --]

From: wang di <di.wang@intel.com>

1. client send create request to the master MDT, which
  will allocate FIDs and create slaves. for all of slaves.

2. Client needs to revalidate slaves during intent getattr
   and open request.

3. lmv_stripe_md will include attributes(size, nlink etc)
   from all of stripe, which will be protected by UPDATE lock.
   client needs to merge these attributes when update inode.

4. send create request to the MDT where the file is located,
   which can help creating master stripe of striped directory.

Signed-off-by: wang di <di.wang@intel.com>
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-3529
Reviewed-on: http://review.whamcloud.com/7196
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>
Signed-off-by: James Simmons <jsimmons@infradead.org>
---
 drivers/staging/lustre/lustre/include/cl_object.h  |    3 +
 .../lustre/lustre/include/lustre/lustre_idl.h      |   40 +++-
 .../lustre/lustre/include/lustre/lustre_user.h     |   16 +-
 drivers/staging/lustre/lustre/include/lustre_lib.h |    2 +
 drivers/staging/lustre/lustre/include/lustre_lmv.h |   59 +++++
 drivers/staging/lustre/lustre/include/obd.h        |   16 +-
 drivers/staging/lustre/lustre/include/obd_class.h  |   19 ++
 drivers/staging/lustre/lustre/llite/dir.c          |   26 ++-
 drivers/staging/lustre/lustre/llite/file.c         |   40 +++-
 .../staging/lustre/lustre/llite/llite_internal.h   |   12 +-
 drivers/staging/lustre/lustre/llite/llite_lib.c    |  193 +++++++++++++++-
 drivers/staging/lustre/lustre/llite/llite_nfs.c    |    7 +-
 drivers/staging/lustre/lustre/llite/namei.c        |   42 +++-
 drivers/staging/lustre/lustre/lmv/lmv_intent.c     |  244 +++++++++++++++++---
 drivers/staging/lustre/lustre/lmv/lmv_internal.h   |   32 +++
 drivers/staging/lustre/lustre/lmv/lmv_obd.c        |  223 +++++++++++++++---
 drivers/staging/lustre/lustre/mdc/mdc_locks.c      |    3 +
 .../staging/lustre/lustre/ptlrpc/pack_generic.c    |   11 +
 18 files changed, 882 insertions(+), 106 deletions(-)

diff --git a/drivers/staging/lustre/lustre/include/cl_object.h b/drivers/staging/lustre/lustre/include/cl_object.h
index 3cd4a25..0fa71a5 100644
--- a/drivers/staging/lustre/lustre/include/cl_object.h
+++ b/drivers/staging/lustre/lustre/include/cl_object.h
@@ -191,6 +191,9 @@ struct cl_attr {
 	 * Group identifier for quota purposes.
 	 */
 	gid_t  cat_gid;
+
+	/* nlink of the directory */
+	__u64  cat_nlink;
 };
 
 /**
diff --git a/drivers/staging/lustre/lustre/include/lustre/lustre_idl.h b/drivers/staging/lustre/lustre/include/lustre/lustre_idl.h
index 0ad6605..a612080 100644
--- a/drivers/staging/lustre/lustre/include/lustre/lustre_idl.h
+++ b/drivers/staging/lustre/lustre/include/lustre/lustre_idl.h
@@ -1610,6 +1610,7 @@ static inline void lmm_oi_cpu_to_le(struct ost_id *dst_oi,
 #define XATTR_NAME_LOV	  "trusted.lov"
 #define XATTR_NAME_LMA	  "trusted.lma"
 #define XATTR_NAME_LMV	  "trusted.lmv"
+#define XATTR_NAME_DEFAULT_LMV	"trusted.dmv"
 #define XATTR_NAME_LINK	 "trusted.link"
 #define XATTR_NAME_FID	  "trusted.fid"
 #define XATTR_NAME_VERSION      "trusted.version"
@@ -2472,7 +2473,7 @@ struct lmv_desc {
 	__u32 ld_tgt_count;		/* how many MDS's */
 	__u32 ld_active_tgt_count;	 /* how many active */
 	__u32 ld_default_stripe_count;     /* how many objects are used */
-	__u32 ld_pattern;		  /* default MEA_MAGIC_* */
+	__u32 ld_pattern;		  /* default hash pattern */
 	__u64 ld_default_hash_size;
 	__u64 ld_padding_1;		/* also fix lustre_swab_lmv_desc */
 	__u32 ld_padding_2;		/* also fix lustre_swab_lmv_desc */
@@ -2486,6 +2487,43 @@ struct lmv_desc {
 #define LMV_MAGIC_V1	0x0CD10CD0	/* normal stripe lmv magic */
 #define LMV_USER_MAGIC	0x0CD20CD0	/* default lmv magic*/
 #define LMV_MAGIC	LMV_MAGIC_V1
+
+enum lmv_hash_type {
+	LMV_HASH_TYPE_ALL_CHARS = 1,
+	LMV_HASH_TYPE_FNV_1A_64 = 2,
+};
+
+#define LMV_HASH_NAME_ALL_CHARS		"all_char"
+#define LMV_HASH_NAME_FNV_1A_64		"fnv_1a_64"
+
+/**
+ * The FNV-1a hash algorithm is as follows:
+ *     hash = FNV_offset_basis
+ *     for each octet_of_data to be hashed
+ *             hash = hash XOR octet_of_data
+ *             hash = hash × FNV_prime
+ *     return hash
+ * http://en.wikipedia.org/wiki/Fowler–Noll–Vo_hash_function#FNV-1a_hash
+ *
+ * http://www.isthe.com/chongo/tech/comp/fnv/index.html#FNV-reference-source
+ * FNV_prime is 2^40 + 2^8 + 0xb3 = 0x100000001b3ULL
+ **/
+#define LUSTRE_FNV_1A_64_PRIME		0x100000001b3ULL
+#define LUSTRE_FNV_1A_64_OFFSET_BIAS	0xcbf29ce484222325ULL
+static inline __u64 lustre_hash_fnv_1a_64(const void *buf, size_t size)
+{
+	__u64 hash = LUSTRE_FNV_1A_64_OFFSET_BIAS;
+	const unsigned char *p = buf;
+	size_t i;
+
+	for (i = 0; i < size; i++) {
+		hash ^= p[i];
+		hash *= LUSTRE_FNV_1A_64_PRIME;
+	}
+
+	return hash;
+}
+
 struct lmv_mds_md_v1 {
 	__u32 lmv_magic;
 	__u32 lmv_stripe_count;		/* stripe count */
diff --git a/drivers/staging/lustre/lustre/include/lustre/lustre_user.h b/drivers/staging/lustre/lustre/include/lustre/lustre_user.h
index ef6f38f..d496d0e 100644
--- a/drivers/staging/lustre/lustre/include/lustre/lustre_user.h
+++ b/drivers/staging/lustre/lustre/include/lustre/lustre_user.h
@@ -374,19 +374,17 @@ struct lov_user_mds_data_v3 {
 } __packed;
 #endif
 
-/* keep this to be the same size as lov_user_ost_data_v1 */
 struct lmv_user_mds_data {
 	struct lu_fid	lum_fid;
 	__u32		lum_padding;
 	__u32		lum_mds;
 };
 
-/* lum_type */
-enum {
-	LMV_STRIPE_TYPE = 0,
-	LMV_DEFAULT_TYPE = 1,
-};
-
+/*
+ * Got this according to how get LOV_MAX_STRIPE_COUNT, see above,
+ * (max buffer size - lmv+rpc header) / sizeof(struct lmv_user_mds_data)
+ */
+#define LMV_MAX_STRIPE_COUNT 2000  /* ((12 * 4096 - 256) / 24) */
 #define lmv_user_md lmv_user_md_v1
 struct lmv_user_md_v1 {
 	__u32	lum_magic;	 /* must be the first field */
@@ -399,7 +397,7 @@ struct lmv_user_md_v1 {
 	__u32	lum_padding3;
 	char	lum_pool_name[LOV_MAXPOOLNAME];
 	struct	lmv_user_mds_data  lum_objects[0];
-};
+} __packed;
 
 static inline int lmv_user_md_size(int stripes, int lmm_magic)
 {
@@ -407,6 +405,8 @@ static inline int lmv_user_md_size(int stripes, int lmm_magic)
 		      stripes * sizeof(struct lmv_user_mds_data);
 }
 
+void lustre_swab_lmv_user_md(struct lmv_user_md *lum);
+
 struct ll_recreate_obj {
 	__u64 lrc_id;
 	__u32 lrc_ost_idx;
diff --git a/drivers/staging/lustre/lustre/include/lustre_lib.h b/drivers/staging/lustre/lustre/include/lustre_lib.h
index 06958f2..def0193 100644
--- a/drivers/staging/lustre/lustre/include/lustre_lib.h
+++ b/drivers/staging/lustre/lustre/include/lustre_lib.h
@@ -391,6 +391,8 @@ static inline void obd_ioctl_freedata(char *buf, int len)
 #define LOVEA_DELETE_VALUES(size, count, offset) (size == 0 && count == 0 && \
 						 offset == (typeof(offset))(-1))
 
+#define LMVEA_DELETE_VALUES(count, offset) ((count) == 0 && \
+					    (offset) == (typeof(offset))(-1))
 /* #define POISON_BULK 0 */
 
 /*
diff --git a/drivers/staging/lustre/lustre/include/lustre_lmv.h b/drivers/staging/lustre/lustre/include/lustre_lmv.h
index 784d67b..4036fce 100644
--- a/drivers/staging/lustre/lustre/include/lustre_lmv.h
+++ b/drivers/staging/lustre/lustre/include/lustre_lmv.h
@@ -66,4 +66,63 @@ static inline void lmv_free_memmd(struct lmv_stripe_md *lsm)
 {
 	lmv_unpack_md(NULL, &lsm, NULL, 0);
 }
+
+static inline void lmv1_cpu_to_le(struct lmv_mds_md_v1 *lmv_dst,
+				  const struct lmv_mds_md_v1 *lmv_src)
+{
+	int i;
+
+	lmv_dst->lmv_magic = cpu_to_le32(lmv_src->lmv_magic);
+	lmv_dst->lmv_stripe_count = cpu_to_le32(lmv_src->lmv_stripe_count);
+	lmv_dst->lmv_master_mdt_index =
+		cpu_to_le32(lmv_src->lmv_master_mdt_index);
+	lmv_dst->lmv_hash_type = cpu_to_le32(lmv_src->lmv_hash_type);
+	lmv_dst->lmv_layout_version = cpu_to_le32(lmv_src->lmv_layout_version);
+
+	for (i = 0; i < lmv_src->lmv_stripe_count; i++)
+		fid_cpu_to_le(&lmv_dst->lmv_stripe_fids[i],
+			      &lmv_src->lmv_stripe_fids[i]);
+}
+
+static inline void lmv1_le_to_cpu(struct lmv_mds_md_v1 *lmv_dst,
+				  const struct lmv_mds_md_v1 *lmv_src)
+{
+	int i;
+
+	lmv_dst->lmv_magic = le32_to_cpu(lmv_src->lmv_magic);
+	lmv_dst->lmv_stripe_count = le32_to_cpu(lmv_src->lmv_stripe_count);
+	lmv_dst->lmv_master_mdt_index =
+		le32_to_cpu(lmv_src->lmv_master_mdt_index);
+	lmv_dst->lmv_hash_type = le32_to_cpu(lmv_src->lmv_hash_type);
+	lmv_dst->lmv_layout_version = le32_to_cpu(lmv_src->lmv_layout_version);
+
+	for (i = 0; i < lmv_src->lmv_stripe_count; i++)
+		fid_le_to_cpu(&lmv_dst->lmv_stripe_fids[i],
+			      &lmv_src->lmv_stripe_fids[i]);
+}
+
+static inline void lmv_cpu_to_le(union lmv_mds_md *lmv_dst,
+				 const union lmv_mds_md *lmv_src)
+{
+	switch (lmv_src->lmv_magic) {
+	case LMV_MAGIC_V1:
+		lmv1_cpu_to_le(&lmv_dst->lmv_md_v1, &lmv_src->lmv_md_v1);
+		break;
+	default:
+		break;
+	}
+}
+
+static inline void lmv_le_to_cpu(union lmv_mds_md *lmv_dst,
+				 const union lmv_mds_md *lmv_src)
+{
+	switch (le32_to_cpu(lmv_src->lmv_magic)) {
+	case LMV_MAGIC_V1:
+		lmv1_le_to_cpu(&lmv_dst->lmv_md_v1, &lmv_src->lmv_md_v1);
+		break;
+	default:
+		break;
+	}
+}
+
 #endif
diff --git a/drivers/staging/lustre/lustre/include/obd.h b/drivers/staging/lustre/lustre/include/obd.h
index 17b8d22..a9f4e13 100644
--- a/drivers/staging/lustre/lustre/include/obd.h
+++ b/drivers/staging/lustre/lustre/include/obd.h
@@ -1022,14 +1022,6 @@ enum {
 };
 
 /* lmv structures */
-#define MEA_MAGIC_LAST_CHAR      0xb2221ca1
-#define MEA_MAGIC_ALL_CHARS      0xb222a11c
-#define MEA_MAGIC_HASH_SEGMENT   0xb222a11b
-
-#define MAX_HASH_SIZE_32	 0x7fffffffUL
-#define MAX_HASH_SIZE	    0x7fffffffffffffffULL
-#define MAX_HASH_HIGHEST_BIT     0x1000000000000000ULL
-
 struct lustre_md {
 	struct mdt_body	 *body;
 	struct lov_stripe_md    *lsm;
@@ -1049,6 +1041,7 @@ struct md_open_data {
 };
 
 struct lookup_intent;
+struct cl_attr;
 
 struct md_ops {
 	int (*getstatus)(struct obd_export *, struct lu_fid *);
@@ -1109,6 +1102,13 @@ struct md_ops {
 
 	int (*free_lustre_md)(struct obd_export *, struct lustre_md *);
 
+	int (*merge_attr)(struct obd_export *,
+			  const struct lmv_stripe_md *lsm,
+			  struct cl_attr *attr);
+
+	int (*update_lsm_md)(struct obd_export *, struct lmv_stripe_md *lsm,
+			     struct mdt_body *, ldlm_blocking_callback);
+
 	int (*set_open_replay_data)(struct obd_export *,
 				    struct obd_client_handle *,
 				    struct lookup_intent *);
diff --git a/drivers/staging/lustre/lustre/include/obd_class.h b/drivers/staging/lustre/lustre/include/obd_class.h
index 6482a93..2f111a8 100644
--- a/drivers/staging/lustre/lustre/include/obd_class.h
+++ b/drivers/staging/lustre/lustre/include/obd_class.h
@@ -1559,6 +1559,25 @@ static inline int md_free_lustre_md(struct obd_export *exp,
 	return MDP(exp->exp_obd, free_lustre_md)(exp, md);
 }
 
+static inline int md_update_lsm_md(struct obd_export *exp,
+				   struct lmv_stripe_md *lsm,
+				   struct mdt_body *body,
+				   ldlm_blocking_callback cb)
+{
+	EXP_CHECK_MD_OP(exp, update_lsm_md);
+	EXP_MD_COUNTER_INCREMENT(exp, update_lsm_md);
+	return MDP(exp->exp_obd, update_lsm_md)(exp, lsm, body, cb);
+}
+
+static inline int md_merge_attr(struct obd_export *exp,
+				const struct lmv_stripe_md *lsm,
+				struct cl_attr *attr)
+{
+	EXP_CHECK_MD_OP(exp, merge_attr);
+	EXP_MD_COUNTER_INCREMENT(exp, merge_attr);
+	return MDP(exp->exp_obd, merge_attr)(exp, lsm, attr);
+}
+
 static inline int md_setxattr(struct obd_export *exp, const struct lu_fid *fid,
 			      u64 valid, const char *name,
 			      const char *input, int input_size,
diff --git a/drivers/staging/lustre/lustre/llite/dir.c b/drivers/staging/lustre/lustre/llite/dir.c
index a72b486..a0560b6 100644
--- a/drivers/staging/lustre/lustre/llite/dir.c
+++ b/drivers/staging/lustre/lustre/llite/dir.c
@@ -668,7 +668,7 @@ static int ll_send_mgc_param(struct obd_export *mgc, char *string)
 }
 
 static int ll_dir_setdirstripe(struct inode *dir, struct lmv_user_md *lump,
-			       char *filename)
+			       const char *filename)
 {
 	struct ptlrpc_request *request = NULL;
 	struct md_op_data *op_data;
@@ -676,6 +676,26 @@ static int ll_dir_setdirstripe(struct inode *dir, struct lmv_user_md *lump,
 	int mode;
 	int err;
 
+	if (unlikely(lump->lum_magic != LMV_USER_MAGIC))
+		return -EINVAL;
+
+	if (lump->lum_stripe_offset == (__u32)-1) {
+		int mdtidx;
+
+		mdtidx = ll_get_mdt_idx(dir);
+		if (mdtidx < 0)
+			return mdtidx;
+
+		lump->lum_stripe_offset = mdtidx;
+	}
+
+	CDEBUG(D_VFSTRACE, "VFS Op:inode="DFID"(%p) name %s stripe_offset %d, stripe_count: %u\n",
+	       PFID(ll_inode2fid(dir)), dir, filename,
+	       (int)lump->lum_stripe_offset, lump->lum_stripe_count);
+
+	if (lump->lum_magic != cpu_to_le32(LMV_USER_MAGIC))
+		lustre_swab_lmv_user_md(lump);
+
 	mode = (~current_umask() & 0755) | S_IFDIR;
 	op_data = ll_prep_md_op_data(NULL, dir, NULL, filename,
 				     strlen(filename), mode, LUSTRE_OPC_MKDIR,
@@ -745,9 +765,6 @@ int ll_dir_setstripe(struct inode *inode, struct lov_user_md *lump,
 	if (IS_ERR(op_data))
 		return PTR_ERR(op_data);
 
-	if (lump && lump->lmm_magic == cpu_to_le32(LMV_USER_MAGIC))
-		op_data->op_cli_flags |= CLI_SET_MEA;
-
 	/* swabbing is done in lov_setstripe() on server side */
 	rc = md_setattr(sbi->ll_md_exp, op_data, lump, lum_size,
 			NULL, 0, &req, NULL);
@@ -1424,7 +1441,6 @@ lmv_out_free:
 		}
 
 		*tmp = lum;
-		tmp->lum_type = LMV_STRIPE_TYPE;
 		tmp->lum_stripe_count = 1;
 		mdtindex = ll_get_mdt_idx(inode);
 		if (mdtindex < 0) {
diff --git a/drivers/staging/lustre/lustre/llite/file.c b/drivers/staging/lustre/lustre/llite/file.c
index 58a7401..18fb713 100644
--- a/drivers/staging/lustre/lustre/llite/file.c
+++ b/drivers/staging/lustre/lustre/llite/file.c
@@ -3015,6 +3015,27 @@ out:
 	return rc;
 }
 
+static int ll_merge_md_attr(struct inode *inode)
+{
+	struct cl_attr attr = { 0 };
+	int rc;
+
+	LASSERT(ll_i2info(inode)->lli_lsm_md);
+	rc = md_merge_attr(ll_i2mdexp(inode), ll_i2info(inode)->lli_lsm_md,
+			   &attr);
+	if (rc)
+		return rc;
+
+	ll_i2info(inode)->lli_stripe_dir_size = attr.cat_size;
+	ll_i2info(inode)->lli_stripe_dir_nlink = attr.cat_nlink;
+
+	ll_i2info(inode)->lli_atime = attr.cat_atime;
+	ll_i2info(inode)->lli_mtime = attr.cat_mtime;
+	ll_i2info(inode)->lli_ctime = attr.cat_ctime;
+
+	return 0;
+}
+
 static int ll_inode_revalidate(struct dentry *dentry, __u64 ibits)
 {
 	struct inode *inode = d_inode(dentry);
@@ -3026,6 +3047,13 @@ static int ll_inode_revalidate(struct dentry *dentry, __u64 ibits)
 
 	/* if object isn't regular file, don't validate size */
 	if (!S_ISREG(inode->i_mode)) {
+		if (S_ISDIR(inode->i_mode) &&
+		    ll_i2info(inode)->lli_lsm_md) {
+			rc = ll_merge_md_attr(inode);
+			if (rc)
+				return rc;
+		}
+
 		LTIME_S(inode->i_atime) = ll_i2info(inode)->lli_atime;
 		LTIME_S(inode->i_mtime) = ll_i2info(inode)->lli_mtime;
 		LTIME_S(inode->i_ctime) = ll_i2info(inode)->lli_ctime;
@@ -3063,7 +3091,6 @@ int ll_getattr(struct vfsmount *mnt, struct dentry *de, struct kstat *stat)
 	else
 		stat->ino = inode->i_ino;
 	stat->mode = inode->i_mode;
-	stat->nlink = inode->i_nlink;
 	stat->uid = inode->i_uid;
 	stat->gid = inode->i_gid;
 	stat->rdev = inode->i_rdev;
@@ -3071,10 +3098,17 @@ int ll_getattr(struct vfsmount *mnt, struct dentry *de, struct kstat *stat)
 	stat->mtime = inode->i_mtime;
 	stat->ctime = inode->i_ctime;
 	stat->blksize = 1 << inode->i_blkbits;
-
-	stat->size = i_size_read(inode);
 	stat->blocks = inode->i_blocks;
 
+	if (S_ISDIR(inode->i_mode) &&
+	    ll_i2info(inode)->lli_lsm_md) {
+		stat->nlink = lli->lli_stripe_dir_nlink;
+		stat->size = lli->lli_stripe_dir_size;
+	} else {
+		stat->nlink = inode->i_nlink;
+		stat->size = i_size_read(inode);
+	}
+
 	return 0;
 }
 
diff --git a/drivers/staging/lustre/lustre/llite/llite_internal.h b/drivers/staging/lustre/lustre/llite/llite_internal.h
index 07b6918..f3b8504 100644
--- a/drivers/staging/lustre/lustre/llite/llite_internal.h
+++ b/drivers/staging/lustre/lustre/llite/llite_internal.h
@@ -39,6 +39,7 @@
 
 /* for struct cl_lock_descr and struct cl_io */
 #include "../include/cl_object.h"
+#include "../include/lustre_lmv.h"
 #include "../include/lustre_mdc.h"
 #include "../include/lustre_intent.h"
 #include <linux/compat.h>
@@ -174,7 +175,11 @@ struct ll_inode_info {
 			 */
 			pid_t			   d_opendir_pid;
 			/* directory stripe information */
-			struct lmv_stripe_md		*d_lmv_md;
+			struct lmv_stripe_md		*d_lsm_md;
+			/* striped directory size */
+			loff_t				d_stripe_size;
+			/* striped directory nlink */
+			__u64				d_stripe_nlink;
 		} d;
 
 #define lli_readdir_mutex       u.d.d_readdir_mutex
@@ -182,7 +187,9 @@ struct ll_inode_info {
 #define lli_sai		 u.d.d_sai
 #define lli_sa_lock	     u.d.d_sa_lock
 #define lli_opendir_pid	 u.d.d_opendir_pid
-#define lli_lmv_md		u.d.d_lmv_md
+#define lli_lsm_md		u.d.d_lsm_md
+#define lli_stripe_dir_size	u.d.d_stripe_size
+#define lli_stripe_dir_nlink	u.d.d_stripe_nlink
 
 		/* for non-directory */
 		struct {
@@ -664,6 +671,7 @@ int ll_objects_destroy(struct ptlrpc_request *request,
 		       struct inode *dir);
 struct inode *ll_iget(struct super_block *sb, ino_t hash,
 		      struct lustre_md *lic);
+int ll_test_inode_by_fid(struct inode *inode, void *opaque);
 int ll_md_blocking_ast(struct ldlm_lock *, struct ldlm_lock_desc *,
 		       void *data, int flag);
 struct dentry *ll_splice_alias(struct inode *inode, struct dentry *de);
diff --git a/drivers/staging/lustre/lustre/llite/llite_lib.c b/drivers/staging/lustre/lustre/llite/llite_lib.c
index eb715be..ef8d87a 100644
--- a/drivers/staging/lustre/lustre/llite/llite_lib.c
+++ b/drivers/staging/lustre/lustre/llite/llite_lib.c
@@ -992,6 +992,188 @@ struct inode *ll_inode_from_resource_lock(struct ldlm_lock *lock)
 	return inode;
 }
 
+static void ll_dir_clear_lsm_md(struct inode *inode)
+{
+	struct ll_inode_info *lli = ll_i2info(inode);
+
+	LASSERT(S_ISDIR(inode->i_mode));
+
+	if (lli->lli_lsm_md) {
+		lmv_free_memmd(lli->lli_lsm_md);
+		lli->lli_lsm_md = NULL;
+	}
+}
+
+static struct inode *ll_iget_anon_dir(struct super_block *sb,
+				      const struct lu_fid *fid,
+				      struct lustre_md *md)
+{
+	struct ll_sb_info *sbi = ll_s2sbi(sb);
+	struct mdt_body *body = md->body;
+	struct inode *inode;
+	ino_t ino;
+
+	ino = cl_fid_build_ino(fid, sbi->ll_flags & LL_SBI_32BIT_API);
+	inode = iget_locked(sb, ino);
+	if (!inode) {
+		CERROR("%s: failed get simple inode "DFID": rc = -ENOENT\n",
+		       ll_get_fsname(sb, NULL, 0), PFID(fid));
+		return ERR_PTR(-ENOENT);
+	}
+
+	if (inode->i_state & I_NEW) {
+		struct ll_inode_info *lli = ll_i2info(inode);
+		struct lmv_stripe_md *lsm = md->lmv;
+
+		inode->i_mode = (inode->i_mode & ~S_IFMT) |
+				(body->mode & S_IFMT);
+		LASSERTF(S_ISDIR(inode->i_mode), "Not slave inode "DFID"\n",
+			 PFID(fid));
+
+		LTIME_S(inode->i_mtime) = 0;
+		LTIME_S(inode->i_atime) = 0;
+		LTIME_S(inode->i_ctime) = 0;
+		inode->i_rdev = 0;
+
+		inode->i_op = &ll_dir_inode_operations;
+		inode->i_fop = &ll_dir_operations;
+		lli->lli_fid = *fid;
+		ll_lli_init(lli);
+
+		LASSERT(lsm);
+		/* master stripe FID */
+		lli->lli_pfid = lsm->lsm_md_oinfo[0].lmo_fid;
+		CDEBUG(D_INODE, "lli %p master "DFID" slave "DFID"\n",
+		       lli, PFID(fid), PFID(&lli->lli_pfid));
+		unlock_new_inode(inode);
+	}
+
+	return inode;
+}
+
+static int ll_init_lsm_md(struct inode *inode, struct lustre_md *md)
+{
+	struct lmv_stripe_md *lsm = md->lmv;
+	struct lu_fid *fid;
+	int i;
+
+	LASSERT(lsm);
+	/*
+	 * XXX sigh, this lsm_root initialization should be in
+	 * LMV layer, but it needs ll_iget right now, so we
+	 * put this here right now.
+	 */
+	for (i = 0; i < lsm->lsm_md_stripe_count; i++) {
+		fid = &lsm->lsm_md_oinfo[i].lmo_fid;
+		LASSERT(!lsm->lsm_md_oinfo[i].lmo_root);
+		if (!i) {
+			lsm->lsm_md_oinfo[i].lmo_root = inode;
+		} else {
+			/*
+			 * Unfortunately ll_iget will call ll_update_inode,
+			 * where the initialization of slave inode is slightly
+			 * different, so it reset lsm_md to NULL to avoid
+			 * initializing lsm for slave inode.
+			 */
+			lsm->lsm_md_oinfo[i].lmo_root =
+				ll_iget_anon_dir(inode->i_sb, fid, md);
+			if (IS_ERR(lsm->lsm_md_oinfo[i].lmo_root)) {
+				int rc = PTR_ERR(lsm->lsm_md_oinfo[i].lmo_root);
+
+				lsm->lsm_md_oinfo[i].lmo_root = NULL;
+				return rc;
+			}
+		}
+	}
+
+	/*
+	 * Here is where the lsm is being initialized(fill lmo_info) after
+	 * client retrieve MD stripe information from MDT.
+	 */
+	return md_update_lsm_md(ll_i2mdexp(inode), lsm, md->body,
+				ll_md_blocking_ast);
+}
+
+static inline int lli_lsm_md_eq(const struct lmv_stripe_md *lsm_md1,
+				const struct lmv_stripe_md *lsm_md2)
+{
+	return lsm_md1->lsm_md_magic == lsm_md2->lsm_md_magic &&
+	       lsm_md1->lsm_md_stripe_count == lsm_md2->lsm_md_stripe_count &&
+	       lsm_md1->lsm_md_master_mdt_index ==
+			lsm_md2->lsm_md_master_mdt_index &&
+	       lsm_md1->lsm_md_hash_type == lsm_md2->lsm_md_hash_type &&
+	       lsm_md1->lsm_md_layout_version ==
+			lsm_md2->lsm_md_layout_version &&
+	       !strcmp(lsm_md1->lsm_md_pool_name,
+		       lsm_md2->lsm_md_pool_name);
+}
+
+static void ll_update_lsm_md(struct inode *inode, struct lustre_md *md)
+{
+	struct ll_inode_info *lli = ll_i2info(inode);
+	struct lmv_stripe_md *lsm = md->lmv;
+	int idx;
+
+	LASSERT(lsm);
+	LASSERT(S_ISDIR(inode->i_mode));
+	if (!lli->lli_lsm_md) {
+		int rc;
+
+		rc = ll_init_lsm_md(inode, md);
+		if (rc) {
+			CERROR("%s: init "DFID" failed: rc = %d\n",
+			       ll_get_fsname(inode->i_sb, NULL, 0),
+			       PFID(&lli->lli_fid), rc);
+			return;
+		}
+		lli->lli_lsm_md = lsm;
+		/*
+		 * set lsm_md to NULL, so the following free lustre_md
+		 * will not free this lsm
+		 */
+		md->lmv = NULL;
+		return;
+	}
+
+	/* Compare the old and new stripe information */
+	if (!lli_lsm_md_eq(lli->lli_lsm_md, lsm)) {
+		CERROR("inode %p %lu mismatch\n"
+		       "    new(%p)     vs     lli_lsm_md(%p):\n"
+		       "    magic:      %x                   %x\n"
+		       "    count:      %x                   %x\n"
+		       "    master:     %x                   %x\n"
+		       "    hash_type:  %x                   %x\n"
+		       "    layout:     %x                   %x\n"
+		       "    pool:       %s                   %s\n",
+		       inode, inode->i_ino, lsm, lli->lli_lsm_md,
+		       lsm->lsm_md_magic, lli->lli_lsm_md->lsm_md_magic,
+		       lsm->lsm_md_stripe_count,
+		       lli->lli_lsm_md->lsm_md_stripe_count,
+		       lsm->lsm_md_master_mdt_index,
+		       lli->lli_lsm_md->lsm_md_master_mdt_index,
+		       lsm->lsm_md_hash_type, lli->lli_lsm_md->lsm_md_hash_type,
+		       lsm->lsm_md_layout_version,
+		       lli->lli_lsm_md->lsm_md_layout_version,
+		       lsm->lsm_md_pool_name,
+		       lli->lli_lsm_md->lsm_md_pool_name);
+		return;
+	}
+
+	for (idx = 0; idx < lli->lli_lsm_md->lsm_md_stripe_count; idx++) {
+		if (!lu_fid_eq(&lli->lli_lsm_md->lsm_md_oinfo[idx].lmo_fid,
+			       &lsm->lsm_md_oinfo[idx].lmo_fid)) {
+			CERROR("%s: FID in lsm mismatch idx %d, old: "DFID" new:"DFID"\n",
+			       ll_get_fsname(inode->i_sb, NULL, 0), idx,
+			       PFID(&lli->lli_lsm_md->lsm_md_oinfo[idx].lmo_fid),
+			       PFID(&lsm->lsm_md_oinfo[idx].lmo_fid));
+			return;
+		}
+	}
+
+	md_update_lsm_md(ll_i2mdexp(inode), ll_i2info(inode)->lli_lsm_md,
+			 md->body, ll_md_blocking_ast);
+}
+
 void ll_clear_inode(struct inode *inode)
 {
 	struct ll_inode_info *lli = ll_i2info(inode);
@@ -1039,7 +1221,9 @@ void ll_clear_inode(struct inode *inode)
 #endif
 	lli->lli_inode_magic = LLI_INODE_DEAD;
 
-	if (!S_ISDIR(inode->i_mode))
+	if (S_ISDIR(inode->i_mode))
+		ll_dir_clear_lsm_md(inode);
+	else
 		LASSERT(list_empty(&lli->lli_agl_list));
 
 	/*
@@ -1484,6 +1668,9 @@ void ll_update_inode(struct inode *inode, struct lustre_md *md)
 			lli->lli_maxbytes = MAX_LFS_FILESIZE;
 	}
 
+	if (S_ISDIR(inode->i_mode) && md->lmv)
+		ll_update_lsm_md(inode, md);
+
 #ifdef CONFIG_FS_POSIX_ACL
 	if (body->valid & OBD_MD_FLACL) {
 		spin_lock(&lli->lli_lock);
@@ -2091,12 +2278,12 @@ struct md_op_data *ll_prep_md_op_data(struct md_op_data *op_data,
 	ll_i2gids(op_data->op_suppgids, i1, i2);
 	op_data->op_fid1 = *ll_inode2fid(i1);
 	if (S_ISDIR(i1->i_mode))
-		op_data->op_mea1 = ll_i2info(i1)->lli_lmv_md;
+		op_data->op_mea1 = ll_i2info(i1)->lli_lsm_md;
 
 	if (i2) {
 		op_data->op_fid2 = *ll_inode2fid(i2);
 		if (S_ISDIR(i2->i_mode))
-			op_data->op_mea2 = ll_i2info(i2)->lli_lmv_md;
+			op_data->op_mea2 = ll_i2info(i2)->lli_lsm_md;
 	} else {
 		fid_zero(&op_data->op_fid2);
 	}
diff --git a/drivers/staging/lustre/lustre/llite/llite_nfs.c b/drivers/staging/lustre/lustre/llite/llite_nfs.c
index 74eb1fc..ab9d5cc 100644
--- a/drivers/staging/lustre/lustre/llite/llite_nfs.c
+++ b/drivers/staging/lustre/lustre/llite/llite_nfs.c
@@ -73,11 +73,6 @@ void get_uuid2fsid(const char *name, int len, __kernel_fsid_t *fsid)
 	fsid->val[1] = key >> 32;
 }
 
-static int ll_nfs_test_inode(struct inode *inode, void *opaque)
-{
-	return lu_fid_eq(&ll_i2info(inode)->lli_fid, opaque);
-}
-
 struct inode *search_inode_for_lustre(struct super_block *sb,
 				      const struct lu_fid *fid)
 {
@@ -92,7 +87,7 @@ struct inode *search_inode_for_lustre(struct super_block *sb,
 
 	CDEBUG(D_INFO, "searching inode for:(%lu,"DFID")\n", hash, PFID(fid));
 
-	inode = ilookup5(sb, hash, ll_nfs_test_inode, (void *)fid);
+	inode = ilookup5(sb, hash, ll_test_inode_by_fid, (void *)fid);
 	if (inode)
 		return inode;
 
diff --git a/drivers/staging/lustre/lustre/llite/namei.c b/drivers/staging/lustre/lustre/llite/namei.c
index 09e1801..1d28714 100644
--- a/drivers/staging/lustre/lustre/llite/namei.c
+++ b/drivers/staging/lustre/lustre/llite/namei.c
@@ -158,6 +158,11 @@ static void ll_invalidate_negative_children(struct inode *dir)
 	spin_unlock(&dir->i_lock);
 }
 
+int ll_test_inode_by_fid(struct inode *inode, void *opaque)
+{
+	return lu_fid_eq(&ll_i2info(inode)->lli_fid, opaque);
+}
+
 int ll_md_blocking_ast(struct ldlm_lock *lock, struct ldlm_lock_desc *desc,
 		       void *data, int flag)
 {
@@ -253,10 +258,41 @@ int ll_md_blocking_ast(struct ldlm_lock *lock, struct ldlm_lock_desc *desc,
 		}
 
 		if ((bits & MDS_INODELOCK_UPDATE) && S_ISDIR(inode->i_mode)) {
-			CDEBUG(D_INODE, "invalidating inode "DFID"\n",
-			       PFID(ll_inode2fid(inode)));
+			struct ll_inode_info *lli = ll_i2info(inode);
+
+			CDEBUG(D_INODE, "invalidating inode "DFID" lli = %p, pfid  = "DFID"\n",
+			       PFID(ll_inode2fid(inode)), lli,
+			       PFID(&lli->lli_pfid));
+
 			truncate_inode_pages(inode->i_mapping, 0);
-			ll_invalidate_negative_children(inode);
+
+			if (unlikely(!fid_is_zero(&lli->lli_pfid))) {
+				struct inode *master_inode = NULL;
+				unsigned long hash;
+
+				/*
+				 * This is slave inode, since all of the child
+				 * dentry is connected on the master inode, so
+				 * we have to invalidate the negative children
+				 * on master inode
+				 */
+				CDEBUG(D_INODE, "Invalidate s"DFID" m"DFID"\n",
+				       PFID(ll_inode2fid(inode)),
+				       PFID(&lli->lli_pfid));
+
+				hash = cl_fid_build_ino(&lli->lli_pfid,
+							ll_need_32bit_api(ll_i2sbi(inode)));
+
+				master_inode = ilookup5(inode->i_sb, hash,
+							ll_test_inode_by_fid,
+							(void *)&lli->lli_pfid);
+				if (master_inode && !IS_ERR(master_inode)) {
+					ll_invalidate_negative_children(master_inode);
+					iput(master_inode);
+				}
+			} else {
+				ll_invalidate_negative_children(inode);
+			}
 		}
 
 		if ((bits & (MDS_INODELOCK_LOOKUP | MDS_INODELOCK_PERM)) &&
diff --git a/drivers/staging/lustre/lustre/lmv/lmv_intent.c b/drivers/staging/lustre/lustre/lmv/lmv_intent.c
index 2f58fda..1b9bbb2 100644
--- a/drivers/staging/lustre/lustre/lmv/lmv_intent.c
+++ b/drivers/staging/lustre/lustre/lmv/lmv_intent.c
@@ -150,6 +150,160 @@ out:
 	return rc;
 }
 
+int lmv_revalidate_slaves(struct obd_export *exp, struct mdt_body *mbody,
+			  struct lmv_stripe_md *lsm,
+			  ldlm_blocking_callback cb_blocking,
+			  int extra_lock_flags)
+{
+	struct obd_device *obd = exp->exp_obd;
+	struct lmv_obd *lmv = &obd->u.lmv;
+	struct mdt_body *body;
+	struct md_op_data *op_data;
+	unsigned long size = 0;
+	unsigned long nlink = 0;
+	__s64 atime = 0;
+	__s64 ctime = 0;
+	__s64 mtime = 0;
+	int rc = 0, i;
+
+	/**
+	 * revalidate slaves has some problems, temporarily return,
+	 * we may not need that
+	 */
+	if (lsm->lsm_md_stripe_count <= 1)
+		return 0;
+
+	op_data = kzalloc(sizeof(*op_data), GFP_NOFS);
+	if (!op_data)
+		return -ENOMEM;
+
+	/**
+	 * Loop over the stripe information, check validity and update them
+	 * from MDS if needed.
+	 */
+	for (i = 0; i < lsm->lsm_md_stripe_count; i++) {
+		struct lookup_intent it = { .it_op = IT_GETATTR };
+		struct ptlrpc_request *req = NULL;
+		struct lustre_handle *lockh = NULL;
+		struct lmv_tgt_desc *tgt = NULL;
+		struct inode *inode;
+		struct lu_fid fid;
+
+		fid = lsm->lsm_md_oinfo[i].lmo_fid;
+		inode = lsm->lsm_md_oinfo[i].lmo_root;
+		if (!i) {
+			if (mbody) {
+				body = mbody;
+				goto update;
+			} else {
+				goto release_lock;
+			}
+		}
+
+		/*
+		 * Prepare op_data for revalidating. Note that @fid2 shluld be
+		 * defined otherwise it will go to server and take new lock
+		 * which is not needed here.
+		 */
+		memset(op_data, 0, sizeof(*op_data));
+		op_data->op_fid1 = fid;
+		op_data->op_fid2 = fid;
+
+		tgt = lmv_locate_mds(lmv, op_data, &fid);
+		if (IS_ERR(tgt)) {
+			rc = PTR_ERR(tgt);
+			goto cleanup;
+		}
+
+		CDEBUG(D_INODE, "Revalidate slave "DFID" -> mds #%d\n",
+		       PFID(&fid), tgt->ltd_idx);
+
+		rc = md_intent_lock(tgt->ltd_exp, op_data, NULL, 0, &it, 0,
+				    &req, cb_blocking, extra_lock_flags);
+		if (rc < 0)
+			goto cleanup;
+
+		lockh = (struct lustre_handle *)&it.it_lock_handle;
+		if (rc > 0 && !req) {
+			/* slave inode is still valid */
+			CDEBUG(D_INODE, "slave "DFID" is still valid.\n",
+			       PFID(&fid));
+			rc = 0;
+		} else {
+			/* refresh slave from server */
+			body = req_capsule_server_get(&req->rq_pill,
+						      &RMF_MDT_BODY);
+			LASSERT(body);
+update:
+			if (unlikely(body->nlink < 2)) {
+				CERROR("%s: nlink %d < 2 corrupt stripe %d "DFID":" DFID"\n",
+				       obd->obd_name, body->nlink, i,
+				       PFID(&lsm->lsm_md_oinfo[i].lmo_fid),
+				       PFID(&lsm->lsm_md_oinfo[0].lmo_fid));
+
+				if (req)
+					ptlrpc_req_finished(req);
+
+				rc = -EIO;
+				goto cleanup;
+			}
+
+			if (i)
+				md_set_lock_data(tgt->ltd_exp, &lockh->cookie,
+						 inode, NULL);
+
+			i_size_write(inode, body->size);
+			set_nlink(inode, body->nlink);
+			LTIME_S(inode->i_atime) = body->atime;
+			LTIME_S(inode->i_ctime) = body->ctime;
+			LTIME_S(inode->i_mtime) = body->mtime;
+
+			if (req)
+				ptlrpc_req_finished(req);
+		}
+release_lock:
+		size += i_size_read(inode);
+
+		if (i != 0)
+			nlink += inode->i_nlink - 2;
+		else
+			nlink += inode->i_nlink;
+
+		atime = LTIME_S(inode->i_atime) > atime ?
+				LTIME_S(inode->i_atime) : atime;
+		ctime = LTIME_S(inode->i_ctime) > ctime ?
+				LTIME_S(inode->i_ctime) : ctime;
+		mtime = LTIME_S(inode->i_mtime) > mtime ?
+				LTIME_S(inode->i_mtime) : mtime;
+
+		if (it.it_lock_mode && lockh) {
+			ldlm_lock_decref(lockh, it.it_lock_mode);
+			it.it_lock_mode = 0;
+		}
+
+		CDEBUG(D_INODE, "i %d "DFID" size %llu, nlink %u, atime %lu, mtime %lu, ctime %lu.\n",
+		       i, PFID(&fid), i_size_read(inode), inode->i_nlink,
+		       LTIME_S(inode->i_atime), LTIME_S(inode->i_mtime),
+		       LTIME_S(inode->i_ctime));
+	}
+
+	/*
+	 * update attr of master request.
+	 */
+	CDEBUG(D_INODE, "Return refreshed attrs: size = %lu nlink %lu atime %llu ctime %llu mtime %llu for " DFID"\n",
+	       size, nlink, atime, ctime, mtime,
+	       PFID(&lsm->lsm_md_oinfo[0].lmo_fid));
+
+	if (mbody) {
+		mbody->atime = atime;
+		mbody->ctime = ctime;
+		mbody->mtime = mtime;
+	}
+cleanup:
+	kfree(op_data);
+	return rc;
+}
+
 /*
  * IT_OPEN is intended to open (and create, possible) an object. Parent (pid)
  * may be split dir.
@@ -166,9 +320,26 @@ static int lmv_intent_open(struct obd_export *exp, struct md_op_data *op_data,
 	struct mdt_body		*body;
 	int			rc;
 
-	tgt = lmv_locate_mds(lmv, op_data, &op_data->op_fid1);
-	if (IS_ERR(tgt))
-		return PTR_ERR(tgt);
+	if (it->it_flags & MDS_OPEN_BY_FID && fid_is_sane(&op_data->op_fid2)) {
+		if (op_data->op_mea1) {
+			struct lmv_stripe_md *lsm = op_data->op_mea1;
+			const struct lmv_oinfo *oinfo;
+
+			oinfo = lsm_name_to_stripe_info(lsm, op_data->op_name,
+							op_data->op_namelen);
+			op_data->op_fid1 = oinfo->lmo_fid;
+		}
+
+		tgt = lmv_find_target(lmv, &op_data->op_fid2);
+		if (IS_ERR(tgt))
+			return PTR_ERR(tgt);
+
+		op_data->op_mds = tgt->ltd_idx;
+	} else {
+		tgt = lmv_locate_mds(lmv, op_data, &op_data->op_fid1);
+		if (IS_ERR(tgt))
+			return PTR_ERR(tgt);
+	}
 
 	/* If it is ready to open the file by FID, do not need
 	 * allocate FID at all, otherwise it will confuse MDT
@@ -205,31 +376,18 @@ static int lmv_intent_open(struct obd_export *exp, struct md_op_data *op_data,
 	body = req_capsule_server_get(&(*reqp)->rq_pill, &RMF_MDT_BODY);
 	if (!body)
 		return -EPROTO;
-	/*
-	 * Not cross-ref case, just get out of here.
-	 */
-	if (likely(!(body->valid & OBD_MD_MDS)))
-		return 0;
 
-	/*
-	 * Okay, MDS has returned success. Probably name has been resolved in
-	 * remote inode.
-	 */
-	rc = lmv_intent_remote(exp, lmm, lmmsize, it, &op_data->op_fid1, flags,
-			       reqp, cb_blocking, extra_lock_flags);
-	if (rc != 0) {
-		LASSERT(rc < 0);
-		/*
-		 * This is possible, that some userspace application will try to
-		 * open file as directory and we will have -ENOTDIR here. As
-		 * this is normal situation, we should not print error here,
-		 * only debug info.
-		 */
-		CDEBUG(D_INODE, "Can't handle remote %s: dir " DFID "(" DFID "):%*s: %d\n",
-		       LL_IT2STR(it), PFID(&op_data->op_fid2),
-		       PFID(&op_data->op_fid1), op_data->op_namelen,
-		       op_data->op_name, rc);
-		return rc;
+	/* Not cross-ref case, just get out of here. */
+	if (unlikely((body->valid & OBD_MD_MDS))) {
+		rc = lmv_intent_remote(exp, lmm, lmmsize, it, &op_data->op_fid1,
+				       flags, reqp, cb_blocking,
+				       extra_lock_flags);
+		if (rc != 0)
+			return rc;
+
+		body = req_capsule_server_get(&(*reqp)->rq_pill, &RMF_MDT_BODY);
+		if (!body)
+			return -EPROTO;
 	}
 
 	return rc;
@@ -269,8 +427,23 @@ static int lmv_intent_lookup(struct obd_export *exp,
 	rc = md_intent_lock(tgt->ltd_exp, op_data, lmm, lmmsize, it,
 			    flags, reqp, cb_blocking, extra_lock_flags);
 
-	if (rc < 0 || !*reqp)
+	if (rc < 0)
+		return rc;
+
+	if (!*reqp) {
+		/*
+		 * If RPC happens, lsm information will be revalidated
+		 * during update_inode process (see ll_update_lsm_md)
+		 */
+		if (op_data->op_mea2) {
+			rc = lmv_revalidate_slaves(exp, NULL, op_data->op_mea2,
+						   cb_blocking,
+						   extra_lock_flags);
+			if (rc != 0)
+				return rc;
+		}
 		return rc;
+	}
 
 	/*
 	 * MDS has returned success. Probably name has been resolved in
@@ -279,12 +452,17 @@ static int lmv_intent_lookup(struct obd_export *exp,
 	body = req_capsule_server_get(&(*reqp)->rq_pill, &RMF_MDT_BODY);
 	if (!body)
 		return -EPROTO;
-	/* Not cross-ref case, just get out of here. */
-	if (likely(!(body->valid & OBD_MD_MDS)))
-		return 0;
 
-	rc = lmv_intent_remote(exp, lmm, lmmsize, it, NULL, flags, reqp,
-			       cb_blocking, extra_lock_flags);
+	/* Not cross-ref case, just get out of here. */
+	if (unlikely((body->valid & OBD_MD_MDS))) {
+		rc = lmv_intent_remote(exp, lmm, lmmsize, it, NULL, flags,
+				       reqp, cb_blocking, extra_lock_flags);
+		if (rc != 0)
+			return rc;
+		body = req_capsule_server_get(&(*reqp)->rq_pill, &RMF_MDT_BODY);
+		if (!body)
+			return -EPROTO;
+	}
 
 	return rc;
 }
diff --git a/drivers/staging/lustre/lustre/lmv/lmv_internal.h b/drivers/staging/lustre/lustre/lmv/lmv_internal.h
index f4c917b..ed02927 100644
--- a/drivers/staging/lustre/lustre/lmv/lmv_internal.h
+++ b/drivers/staging/lustre/lustre/lmv/lmv_internal.h
@@ -55,6 +55,14 @@ int __lmv_fid_alloc(struct lmv_obd *lmv, struct lu_fid *fid, u32 mds);
 int lmv_fid_alloc(struct obd_export *exp, struct lu_fid *fid,
 		  struct md_op_data *op_data);
 
+int lmv_unpack_md(struct obd_export *exp, struct lmv_stripe_md **lsmp,
+		  const union lmv_mds_md *lmm, int stripe_count);
+
+int lmv_revalidate_slaves(struct obd_export *exp, struct mdt_body *mbody,
+			  struct lmv_stripe_md *lsm,
+			  ldlm_blocking_callback cb_blocking,
+			  int extra_lock_flags);
+
 static inline struct lmv_tgt_desc *
 lmv_get_target(struct lmv_obd *lmv, u32 mds)
 {
@@ -94,6 +102,30 @@ static inline int lmv_stripe_md_size(int stripe_count)
 	return sizeof(*lsm) + stripe_count * sizeof(lsm->lsm_md_oinfo[0]);
 }
 
+int lmv_name_to_stripe_index(enum lmv_hash_type hashtype,
+			     unsigned int max_mdt_index,
+			     const char *name, int namelen);
+
+static inline const struct lmv_oinfo *
+lsm_name_to_stripe_info(const struct lmv_stripe_md *lsm, const char *name,
+			int namelen)
+{
+	int stripe_index;
+
+	stripe_index = lmv_name_to_stripe_index(lsm->lsm_md_hash_type,
+						lsm->lsm_md_stripe_count,
+						name, namelen);
+	if (stripe_index < 0)
+		return ERR_PTR(stripe_index);
+
+	LASSERTF(stripe_index < lsm->lsm_md_stripe_count,
+		 "stripe_index = %d, stripe_count = %d hash_type = %x name = %.*s\n",
+		 stripe_index, lsm->lsm_md_stripe_count,
+		 lsm->lsm_md_hash_type, namelen, name);
+
+	return &lsm->lsm_md_oinfo[stripe_index];
+}
+
 struct lmv_tgt_desc
 *lmv_locate_mds(struct lmv_obd *lmv, struct md_op_data *op_data,
 		struct lu_fid *fid);
diff --git a/drivers/staging/lustre/lustre/lmv/lmv_obd.c b/drivers/staging/lustre/lustre/lmv/lmv_obd.c
index 6be2afc..df29ad5 100644
--- a/drivers/staging/lustre/lustre/lmv/lmv_obd.c
+++ b/drivers/staging/lustre/lustre/lmv/lmv_obd.c
@@ -48,11 +48,65 @@
 #include "../include/obd_class.h"
 #include "../include/lustre_lmv.h"
 #include "../include/lprocfs_status.h"
+#include "../include/cl_object.h"
 #include "../include/lustre_lite.h"
 #include "../include/lustre_fid.h"
 #include "../include/lustre_kernelcomm.h"
 #include "lmv_internal.h"
 
+/* This hash is only for testing purpose */
+static inline unsigned int
+lmv_hash_all_chars(unsigned int count, const char *name, int namelen)
+{
+	const unsigned char *p = (const unsigned char *)name;
+	unsigned int c = 0;
+
+	while (--namelen >= 0)
+		c += p[namelen];
+
+	c = c % count;
+
+	return c;
+}
+
+static inline unsigned int
+lmv_hash_fnv1a(unsigned int count, const char *name, int namelen)
+{
+	__u64 hash;
+
+	hash = lustre_hash_fnv_1a_64(name, namelen);
+
+	hash = hash % count;
+
+	return hash;
+}
+
+int lmv_name_to_stripe_index(enum lmv_hash_type hashtype,
+			     unsigned int max_mdt_index,
+			     const char *name, int namelen)
+{
+	int idx;
+
+	LASSERT(namelen > 0);
+	if (max_mdt_index <= 1)
+		return 0;
+
+	switch (hashtype) {
+	case LMV_HASH_TYPE_ALL_CHARS:
+		idx = lmv_hash_all_chars(max_mdt_index, name, namelen);
+		break;
+	case LMV_HASH_TYPE_FNV_1A_64:
+		idx = lmv_hash_fnv1a(max_mdt_index, name, namelen);
+		break;
+	default:
+		CERROR("Unknown hash type 0x%x\n", hashtype);
+		return -EINVAL;
+	}
+
+	LASSERT(idx < max_mdt_index);
+	return idx;
+}
+
 static void lmv_activate_target(struct lmv_obd *lmv,
 				struct lmv_tgt_desc *tgt,
 				int activate)
@@ -1174,28 +1228,19 @@ static int lmv_placement_policy(struct obd_device *obd,
 	 * If stripe_offset is provided during setdirstripe
 	 * (setdirstripe -i xx), xx MDS will be chosen.
 	 */
-	if (op_data->op_cli_flags & CLI_SET_MEA) {
+	if (op_data->op_cli_flags & CLI_SET_MEA && op_data->op_data) {
 		struct lmv_user_md *lum;
 
-		lum = (struct lmv_user_md *)op_data->op_data;
-		if (lum->lum_type == LMV_STRIPE_TYPE &&
-		    lum->lum_stripe_offset != -1) {
-			if (lum->lum_stripe_offset >= lmv->desc.ld_tgt_count) {
-				CERROR("%s: Stripe_offset %d > MDT count %d: rc = %d\n",
-				       obd->obd_name,
-				       lum->lum_stripe_offset,
-				       lmv->desc.ld_tgt_count, -ERANGE);
-				return -ERANGE;
-			}
-			*mds = lum->lum_stripe_offset;
-			return 0;
-		}
+		lum = op_data->op_data;
+		*mds = lum->lum_stripe_offset;
+	} else {
+		/*
+		 * Allocate new fid on target according to operation type and
+		 * parent home mds.
+		 */
+		*mds = op_data->op_mds;
 	}
 
-	/* Allocate new fid on target according to operation type and parent
-	 * home mds.
-	 */
-	*mds = op_data->op_mds;
 	return 0;
 }
 
@@ -1597,17 +1642,38 @@ static int lmv_close(struct obd_export *exp, struct md_op_data *op_data,
 	return rc;
 }
 
+/**
+ * Choosing the MDT by name or FID in @op_data.
+ * For non-striped directory, it will locate MDT by fid.
+ * For striped-directory, it will locate MDT by name. And also
+ * it will reset op_fid1 with the FID of the chosen stripe.
+ **/
 struct lmv_tgt_desc
 *lmv_locate_mds(struct lmv_obd *lmv, struct md_op_data *op_data,
 		struct lu_fid *fid)
 {
+	struct lmv_stripe_md *lsm = op_data->op_mea1;
+	const struct lmv_oinfo *oinfo;
 	struct lmv_tgt_desc *tgt;
 
-	tgt = lmv_find_target(lmv, fid);
-	if (IS_ERR(tgt))
+	if (!lsm || lsm->lsm_md_stripe_count <= 1 ||
+	    !op_data->op_namelen) {
+		tgt = lmv_find_target(lmv, fid);
+		if (IS_ERR(tgt))
+			return tgt;
+
+		op_data->op_mds = tgt->ltd_idx;
+
 		return tgt;
+	}
 
-	op_data->op_mds = tgt->ltd_idx;
+	oinfo = lsm_name_to_stripe_info(lsm, op_data->op_name,
+					op_data->op_namelen);
+	*fid = oinfo->lmo_fid;
+	op_data->op_mds = oinfo->lmo_mds;
+	tgt = lmv_get_target(lmv, op_data->op_mds);
+
+	CDEBUG(D_INFO, "locate on mds %u\n", op_data->op_mds);
 
 	return tgt;
 }
@@ -1633,13 +1699,26 @@ static int lmv_create(struct obd_export *exp, struct md_op_data *op_data,
 	if (IS_ERR(tgt))
 		return PTR_ERR(tgt);
 
+	CDEBUG(D_INODE, "CREATE name '%.*s' on "DFID" -> mds #%x\n",
+	       op_data->op_namelen, op_data->op_name, PFID(&op_data->op_fid1),
+	       op_data->op_mds);
+
 	rc = lmv_fid_alloc(exp, &op_data->op_fid2, op_data);
 	if (rc)
 		return rc;
 
-	CDEBUG(D_INODE, "CREATE '%*s' on "DFID" -> mds #%x\n",
-	       op_data->op_namelen, op_data->op_name, PFID(&op_data->op_fid1),
-	       op_data->op_mds);
+	/*
+	 * Send the create request to the MDT where the object
+	 * will be located
+	 */
+	tgt = lmv_find_target(lmv, &op_data->op_fid2);
+	if (IS_ERR(tgt))
+		return PTR_ERR(tgt);
+
+	op_data->op_mds = tgt->ltd_idx;
+
+	CDEBUG(D_INODE, "CREATE obj "DFID" -> mds #%x\n",
+	       PFID(&op_data->op_fid1), op_data->op_mds);
 
 	op_data->op_flags |= MF_MDC_CANCEL_FID1;
 	rc = md_create(tgt->ltd_exp, op_data, data, datalen, mode, uid, gid,
@@ -1889,6 +1968,15 @@ static int lmv_link(struct obd_export *exp, struct md_op_data *op_data,
 	op_data->op_fsuid = from_kuid(&init_user_ns, current_fsuid());
 	op_data->op_fsgid = from_kgid(&init_user_ns, current_fsgid());
 	op_data->op_cap = cfs_curproc_cap_pack();
+	if (op_data->op_mea2) {
+		struct lmv_stripe_md *lsm = op_data->op_mea2;
+		const struct lmv_oinfo *oinfo;
+
+		oinfo = lsm_name_to_stripe_info(lsm, op_data->op_name,
+						op_data->op_namelen);
+		op_data->op_fid2 = oinfo->lmo_fid;
+	}
+
 	tgt = lmv_locate_mds(lmv, op_data, &op_data->op_fid2);
 	if (IS_ERR(tgt))
 		return PTR_ERR(tgt);
@@ -1914,14 +2002,15 @@ static int lmv_rename(struct obd_export *exp, struct md_op_data *op_data,
 	struct obd_device       *obd = exp->exp_obd;
 	struct lmv_obd	  *lmv = &obd->u.lmv;
 	struct lmv_tgt_desc     *src_tgt;
-	struct lmv_tgt_desc     *tgt_tgt;
 	int			rc;
 
 	LASSERT(oldlen != 0);
 
-	CDEBUG(D_INODE, "RENAME %*s in "DFID" to %*s in "DFID"\n",
+	CDEBUG(D_INODE, "RENAME %.*s in "DFID":%d to %.*s in "DFID":%d\n",
 	       oldlen, old, PFID(&op_data->op_fid1),
-	       newlen, new, PFID(&op_data->op_fid2));
+	       op_data->op_mea1 ? op_data->op_mea1->lsm_md_stripe_count : 0,
+	       newlen, new, PFID(&op_data->op_fid2),
+	       op_data->op_mea2 ? op_data->op_mea2->lsm_md_stripe_count : 0);
 
 	rc = lmv_check_connect(obd);
 	if (rc)
@@ -1930,13 +2019,33 @@ static int lmv_rename(struct obd_export *exp, struct md_op_data *op_data,
 	op_data->op_fsuid = from_kuid(&init_user_ns, current_fsuid());
 	op_data->op_fsgid = from_kgid(&init_user_ns, current_fsgid());
 	op_data->op_cap = cfs_curproc_cap_pack();
-	src_tgt = lmv_locate_mds(lmv, op_data, &op_data->op_fid1);
-	if (IS_ERR(src_tgt))
-		return PTR_ERR(src_tgt);
 
-	tgt_tgt = lmv_locate_mds(lmv, op_data, &op_data->op_fid2);
-	if (IS_ERR(tgt_tgt))
-		return PTR_ERR(tgt_tgt);
+	if (op_data->op_mea1) {
+		struct lmv_stripe_md *lsm = op_data->op_mea1;
+		const struct lmv_oinfo *oinfo;
+
+		oinfo = lsm_name_to_stripe_info(lsm, old, oldlen);
+		op_data->op_fid1 = oinfo->lmo_fid;
+		op_data->op_mds = oinfo->lmo_mds;
+		src_tgt = lmv_get_target(lmv, op_data->op_mds);
+		if (IS_ERR(src_tgt))
+			return PTR_ERR(src_tgt);
+	} else {
+		src_tgt = lmv_find_target(lmv, &op_data->op_fid1);
+		if (IS_ERR(src_tgt))
+			return PTR_ERR(src_tgt);
+
+		op_data->op_mds = src_tgt->ltd_idx;
+	}
+
+	if (op_data->op_mea2) {
+		struct lmv_stripe_md *lsm = op_data->op_mea2;
+		const struct lmv_oinfo *oinfo;
+
+		oinfo = lsm_name_to_stripe_info(lsm, new, newlen);
+		op_data->op_fid2 = oinfo->lmo_fid;
+	}
+
 	/*
 	 * LOOKUP lock on src child (fid3) should also be cancelled for
 	 * src_tgt in mdc_rename.
@@ -2568,6 +2677,7 @@ int lmv_unpack_md(struct obd_export *exp, struct lmv_stripe_md **lsmp,
 	}
 	return lsm_size;
 }
+EXPORT_SYMBOL(lmv_unpack_md);
 
 int lmv_unpackmd(struct obd_export *exp, struct lov_stripe_md **lsmp,
 		 struct lov_mds_md *lmm, int disk_len)
@@ -2741,7 +2851,7 @@ static int lmv_intent_getattr_async(struct obd_export *exp,
 	if (rc)
 		return rc;
 
-	tgt = lmv_find_target(lmv, &op_data->op_fid1);
+	tgt = lmv_locate_mds(lmv, op_data, &op_data->op_fid1);
 	if (IS_ERR(tgt))
 		return PTR_ERR(tgt);
 
@@ -2843,6 +2953,49 @@ static int lmv_quotacheck(struct obd_device *unused, struct obd_export *exp,
 	return rc;
 }
 
+int lmv_update_lsm_md(struct obd_export *exp, struct lmv_stripe_md *lsm,
+		      struct mdt_body *body, ldlm_blocking_callback cb_blocking)
+{
+	if (lsm->lsm_md_stripe_count <= 1)
+		return 0;
+
+	return lmv_revalidate_slaves(exp, body, lsm, cb_blocking, 0);
+}
+
+int lmv_merge_attr(struct obd_export *exp, const struct lmv_stripe_md *lsm,
+		   struct cl_attr *attr)
+{
+	int i;
+
+	for (i = 0; i < lsm->lsm_md_stripe_count; i++) {
+		struct inode *inode = lsm->lsm_md_oinfo[i].lmo_root;
+
+		CDEBUG(D_INFO, ""DFID" size %llu, nlink %u, atime %lu ctime %lu, mtime %lu.\n",
+		       PFID(&lsm->lsm_md_oinfo[i].lmo_fid),
+		       i_size_read(inode), inode->i_nlink,
+		       LTIME_S(inode->i_atime), LTIME_S(inode->i_ctime),
+		       LTIME_S(inode->i_mtime));
+
+		/* for slave stripe, it needs to subtract nlink for . and .. */
+		if (i)
+			attr->cat_nlink += inode->i_nlink - 2;
+		else
+			attr->cat_nlink = inode->i_nlink;
+
+		attr->cat_size += i_size_read(inode);
+
+		if (attr->cat_atime < LTIME_S(inode->i_atime))
+			attr->cat_atime = LTIME_S(inode->i_atime);
+
+		if (attr->cat_ctime < LTIME_S(inode->i_ctime))
+			attr->cat_ctime = LTIME_S(inode->i_ctime);
+
+		if (attr->cat_mtime < LTIME_S(inode->i_mtime))
+			attr->cat_mtime = LTIME_S(inode->i_mtime);
+	}
+	return 0;
+}
+
 static struct obd_ops lmv_obd_ops = {
 	.owner		= THIS_MODULE,
 	.setup		= lmv_setup,
@@ -2888,6 +3041,8 @@ static struct md_ops lmv_md_ops = {
 	.lock_match		= lmv_lock_match,
 	.get_lustre_md		= lmv_get_lustre_md,
 	.free_lustre_md		= lmv_free_lustre_md,
+	.update_lsm_md		= lmv_update_lsm_md,
+	.merge_attr		= lmv_merge_attr,
 	.set_open_replay_data	= lmv_set_open_replay_data,
 	.clear_open_replay_data	= lmv_clear_open_replay_data,
 	.intent_getattr_async	= lmv_intent_getattr_async,
diff --git a/drivers/staging/lustre/lustre/mdc/mdc_locks.c b/drivers/staging/lustre/lustre/mdc/mdc_locks.c
index 06a1274..626fce5 100644
--- a/drivers/staging/lustre/lustre/mdc/mdc_locks.c
+++ b/drivers/staging/lustre/lustre/mdc/mdc_locks.c
@@ -325,6 +325,9 @@ static struct ptlrpc_request *mdc_intent_open_pack(struct obd_export *exp,
 	mdc_open_pack(req, op_data, it->it_create_mode, 0, it->it_flags, lmm,
 		      lmmsize);
 
+	req_capsule_set_size(&req->rq_pill, &RMF_MDT_MD, RCL_SERVER,
+			     obddev->u.cli.cl_max_mds_easize);
+
 	ptlrpc_request_set_replen(req);
 	return req;
 }
diff --git a/drivers/staging/lustre/lustre/ptlrpc/pack_generic.c b/drivers/staging/lustre/lustre/ptlrpc/pack_generic.c
index b514f18..07e23d1 100644
--- a/drivers/staging/lustre/lustre/ptlrpc/pack_generic.c
+++ b/drivers/staging/lustre/lustre/ptlrpc/pack_generic.c
@@ -1878,6 +1878,17 @@ void lustre_swab_lov_desc(struct lov_desc *ld)
 }
 EXPORT_SYMBOL(lustre_swab_lov_desc);
 
+void lustre_swab_lmv_user_md(struct lmv_user_md *lum)
+{
+	__swab32s(&lum->lum_magic);
+	__swab32s(&lum->lum_stripe_count);
+	__swab32s(&lum->lum_stripe_offset);
+	__swab32s(&lum->lum_hash_type);
+	__swab32s(&lum->lum_type);
+	CLASSERT(offsetof(typeof(*lum), lum_padding1));
+}
+EXPORT_SYMBOL(lustre_swab_lmv_user_md);
+
 static void print_lum(struct lov_user_md *lum)
 {
 	CDEBUG(D_OTHER, "lov_user_md %p:\n", lum);
-- 
1.7.1

[PATCH 31/58] staging: lustre: llite: fix "getdirstripe" to show stripe info

[James Simmons]

From: wang di <di.wang@intel.com>

Fix "lfs getdirstripe", so it can show layout information
of striped directory

[root@testnode tests]# ../utils/lfs getdirstripe /mnt/lustre/test1
/mnt/lustre/test1
lmv_stripe_count: 2
lmv_stripe_offset: 0
mdtidx               FID[seq:oid:ver]
     0               [0x280000400:0x1:0x0]
     1               [0x2c0000400:0x1:0x0]

Signed-off-by: wang di <di.wang@intel.com>
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-3531
Reviewed-on: http://review.whamcloud.com/7228
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>
Reviewed-by: Alex Zhuravlev <alexey.zhuravlev@intel.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
Signed-off-by: James Simmons <jsimmons@infradead.org>
---
 .../lustre/lustre/include/lustre/lustre_idl.h      |    4 +
 .../lustre/lustre/include/lustre/lustre_user.h     |    1 +
 drivers/staging/lustre/lustre/llite/dir.c          |  184 +++++++++++++++-----
 .../staging/lustre/lustre/llite/llite_internal.h   |    4 +-
 drivers/staging/lustre/lustre/llite/xattr.c        |    7 +-
 .../staging/lustre/lustre/ptlrpc/pack_generic.c    |   26 +++
 6 files changed, 180 insertions(+), 46 deletions(-)

diff --git a/drivers/staging/lustre/lustre/include/lustre/lustre_idl.h b/drivers/staging/lustre/lustre/include/lustre/lustre_idl.h
index a612080..0ff30c6 100644
--- a/drivers/staging/lustre/lustre/include/lustre/lustre_idl.h
+++ b/drivers/staging/lustre/lustre/include/lustre/lustre_idl.h
@@ -1728,6 +1728,8 @@ lov_mds_md_max_stripe_count(size_t buf_size, __u32 lmm_magic)
 #define OBD_MD_FLDATAVERSION (0x0010000000000000ULL) /* iversion sum */
 #define OBD_MD_FLRELEASED    (0x0020000000000000ULL) /* file released */
 
+#define OBD_MD_DEFAULT_MEA   (0x0040000000000000ULL) /* default MEA */
+
 #define OBD_MD_FLGETATTR (OBD_MD_FLID    | OBD_MD_FLATIME | OBD_MD_FLMTIME | \
 			  OBD_MD_FLCTIME | OBD_MD_FLSIZE  | OBD_MD_FLBLKSZ | \
 			  OBD_MD_FLMODE  | OBD_MD_FLTYPE  | OBD_MD_FLUID   | \
@@ -2543,6 +2545,8 @@ union lmv_mds_md {
 	struct lmv_user_md	lmv_user_md;
 };
 
+void lustre_swab_lmv_mds_md(union lmv_mds_md *lmm);
+
 static inline ssize_t lmv_mds_md_size(int stripe_count, unsigned int lmm_magic)
 {
 	ssize_t len = -EINVAL;
diff --git a/drivers/staging/lustre/lustre/include/lustre/lustre_user.h b/drivers/staging/lustre/lustre/include/lustre/lustre_user.h
index d496d0e..26dbda0 100644
--- a/drivers/staging/lustre/lustre/include/lustre/lustre_user.h
+++ b/drivers/staging/lustre/lustre/include/lustre/lustre_user.h
@@ -242,6 +242,7 @@ struct ost_id {
 #define LL_IOC_SET_LEASE		_IOWR('f', 243, long)
 #define LL_IOC_GET_LEASE		_IO('f', 244)
 #define LL_IOC_HSM_IMPORT		_IOWR('f', 245, struct hsm_user_import)
+#define LL_IOC_LMV_SET_DEFAULT_STRIPE	_IOWR('f', 246, struct lmv_user_md)
 
 #define LL_STATFS_LMV	   1
 #define LL_STATFS_LOV	   2
diff --git a/drivers/staging/lustre/lustre/llite/dir.c b/drivers/staging/lustre/lustre/llite/dir.c
index a0560b6..5288750 100644
--- a/drivers/staging/lustre/lustre/llite/dir.c
+++ b/drivers/staging/lustre/lustre/llite/dir.c
@@ -749,6 +749,13 @@ int ll_dir_setstripe(struct inode *inode, struct lov_user_md *lump,
 			lum_size = sizeof(struct lov_user_md_v3);
 			break;
 		}
+		case LMV_USER_MAGIC: {
+			if (lump->lmm_magic != cpu_to_le32(LMV_USER_MAGIC))
+				lustre_swab_lmv_user_md(
+					(struct lmv_user_md *)lump);
+			lum_size = sizeof(struct lmv_user_md);
+			break;
+		}
 		default: {
 			CDEBUG(D_IOCTL, "bad userland LOV MAGIC: %#08x != %#08x nor %#08x\n",
 			       lump->lmm_magic, LOV_USER_MAGIC_V1,
@@ -819,8 +826,16 @@ end:
 	return rc;
 }
 
-int ll_dir_getstripe(struct inode *inode, struct lov_mds_md **lmmp,
-		     int *lmm_size, struct ptlrpc_request **request)
+/**
+ * This function will be used to get default LOV/LMV/Default LMV
+ * @valid will be used to indicate which stripe it will retrieve
+ *	OBD_MD_MEA		LMV stripe EA
+ *	OBD_MD_DEFAULT_MEA	Default LMV stripe EA
+ *	otherwise		Default LOV EA.
+ * Each time, it can only retrieve 1 stripe EA
+ **/
+int ll_dir_getstripe(struct inode *inode, void **plmm, int *plmm_size,
+		     struct ptlrpc_request **request, u64 valid)
 {
 	struct ll_sb_info *sbi = ll_i2sbi(inode);
 	struct mdt_body   *body;
@@ -829,7 +844,7 @@ int ll_dir_getstripe(struct inode *inode, struct lov_mds_md **lmmp,
 	int rc, lmmsize;
 	struct md_op_data *op_data;
 
-	rc = ll_get_default_mdsize(sbi, &lmmsize);
+	rc = ll_get_max_mdsize(sbi, &lmmsize);
 	if (rc)
 		return rc;
 
@@ -860,6 +875,7 @@ int ll_dir_getstripe(struct inode *inode, struct lov_mds_md **lmmp,
 
 	lmm = req_capsule_server_sized_get(&req->rq_pill,
 					   &RMF_MDT_MD, lmmsize);
+	LASSERT(lmm);
 
 	/*
 	 * This is coming from the MDS, so is probably in
@@ -876,40 +892,48 @@ int ll_dir_getstripe(struct inode *inode, struct lov_mds_md **lmmp,
 		if (cpu_to_le32(LOV_MAGIC) != LOV_MAGIC)
 			lustre_swab_lov_user_md_v3((struct lov_user_md_v3 *)lmm);
 		break;
+	case LMV_USER_MAGIC:
+		if (cpu_to_le32(LMV_USER_MAGIC) != LMV_USER_MAGIC)
+			lustre_swab_lmv_user_md((struct lmv_user_md *)lmm);
+		break;
 	default:
 		CERROR("unknown magic: %lX\n", (unsigned long)lmm->lmm_magic);
 		rc = -EPROTO;
 	}
 out:
-	*lmmp = lmm;
-	*lmm_size = lmmsize;
+	*plmm = lmm;
+	*plmm_size = lmmsize;
 	*request = req;
 	return rc;
 }
 
-/*
- *  Get MDT index for the inode.
- */
-int ll_get_mdt_idx(struct inode *inode)
+static int ll_get_mdt_idx_by_fid(struct ll_sb_info *sbi,
+				 const struct lu_fid *fid)
 {
-	struct ll_sb_info *sbi = ll_i2sbi(inode);
 	struct md_op_data *op_data;
-	int rc, mdtidx;
+	int mdt_index, rc;
 
-	op_data = ll_prep_md_op_data(NULL, inode, NULL, NULL, 0,
-				     0, LUSTRE_OPC_ANY, NULL);
-	if (IS_ERR(op_data))
-		return PTR_ERR(op_data);
+	op_data = kzalloc(sizeof(*op_data), GFP_NOFS);
+	if (!op_data)
+		return -ENOMEM;
 
 	op_data->op_flags |= MF_GET_MDT_IDX;
+	op_data->op_fid1 = *fid;
 	rc = md_getattr(sbi->ll_md_exp, op_data, NULL);
-	mdtidx = op_data->op_mds;
-	ll_finish_md_op_data(op_data);
-	if (rc < 0) {
-		CDEBUG(D_INFO, "md_getattr_name: %d\n", rc);
+	mdt_index = op_data->op_mds;
+	kvfree(op_data);
+	if (rc < 0)
 		return rc;
-	}
-	return mdtidx;
+
+	return mdt_index;
+}
+
+/*
+ *  Get MDT index for the inode.
+ */
+int ll_get_mdt_idx(struct inode *inode)
+{
+	return ll_get_mdt_idx_by_fid(ll_i2sbi(inode), ll_inode2fid(inode));
 }
 
 /**
@@ -1391,6 +1415,22 @@ lmv_out_free:
 		obd_ioctl_freedata(buf, len);
 		return rc;
 	}
+	case LL_IOC_LMV_SET_DEFAULT_STRIPE: {
+		struct lmv_user_md __user *ulump;
+		struct lmv_user_md lum;
+		int rc;
+
+		ulump = (struct lmv_user_md __user *)arg;
+		if (copy_from_user(&lum, ulump, sizeof(lum)))
+			return -EFAULT;
+
+		if (lum.lum_magic != LMV_USER_MAGIC)
+			return -EINVAL;
+
+		rc = ll_dir_setstripe(inode, (struct lov_user_md *)&lum, 0);
+
+		return rc;
+	}
 	case LL_IOC_LOV_SETSTRIPE: {
 		struct lov_user_md_v3 lumv3;
 		struct lov_user_md_v1 *lumv1 = (struct lov_user_md_v1 *)&lumv3;
@@ -1420,46 +1460,107 @@ lmv_out_free:
 		return rc;
 	}
 	case LL_IOC_LMV_GETSTRIPE: {
-		struct lmv_user_md __user *lump = (void __user *)arg;
+		struct lmv_user_md __user *ulmv;
 		struct lmv_user_md lum;
-		struct lmv_user_md *tmp;
+		struct ptlrpc_request *request = NULL;
+		struct lmv_user_md *tmp = NULL;
+		union lmv_mds_md *lmm = NULL;
+		u64 valid = 0;
+		int stripe_count;
+		int mdt_index;
 		int lum_size;
-		int rc = 0;
-		int mdtindex;
+		int lmmsize;
+		int rc;
+		int i;
 
-		if (copy_from_user(&lum, lump, sizeof(struct lmv_user_md)))
+		ulmv = (struct lmv_user_md __user *)arg;
+		if (copy_from_user(&lum, ulmv, sizeof(*ulmv)))
 			return -EFAULT;
 
-		if (lum.lum_magic != LMV_MAGIC_V1)
+		/*
+		 * lum_magic will indicate which stripe the ioctl will like
+		 * to get, LMV_MAGIC_V1 is for normal LMV stripe, LMV_USER_MAGIC
+		 * is for default LMV stripe
+		 */
+		if (lum.lum_magic == LMV_MAGIC_V1)
+			valid |= OBD_MD_MEA;
+		else if (lum.lum_magic == LMV_USER_MAGIC)
+			valid |= OBD_MD_DEFAULT_MEA;
+		else
 			return -EINVAL;
 
-		lum_size = lmv_user_md_size(1, LMV_MAGIC_V1);
+		rc = ll_dir_getstripe(inode, (void **)&lmm, &lmmsize, &request,
+				      valid);
+		if (rc && rc != -ENODATA)
+			goto finish_req;
+
+		/* Get default LMV EA */
+		if (lum.lum_magic == LMV_USER_MAGIC) {
+			if (rc)
+				goto finish_req;
+
+			if (lmmsize > sizeof(*ulmv)) {
+				rc = -EINVAL;
+				goto finish_req;
+			}
+
+			if (copy_to_user(ulmv, lmm, lmmsize))
+				rc = -EFAULT;
+
+			goto finish_req;
+		}
+
+		/* Get normal LMV EA */
+		if (rc == -ENODATA) {
+			stripe_count = 1;
+		} else {
+			LASSERT(lmm);
+			stripe_count = lmv_mds_md_stripe_count_get(lmm);
+		}
+
+		lum_size = lmv_user_md_size(stripe_count, LMV_MAGIC_V1);
 		tmp = kzalloc(lum_size, GFP_NOFS);
 		if (!tmp) {
 			rc = -ENOMEM;
-			goto free_lmv;
+			goto finish_req;
 		}
 
-		*tmp = lum;
+		tmp->lum_magic = LMV_MAGIC_V1;
 		tmp->lum_stripe_count = 1;
-		mdtindex = ll_get_mdt_idx(inode);
-		if (mdtindex < 0) {
+		mdt_index = ll_get_mdt_idx(inode);
+		if (mdt_index < 0) {
 			rc = -ENOMEM;
-			goto free_lmv;
+			goto out_tmp;
+		}
+		tmp->lum_stripe_offset = mdt_index;
+		tmp->lum_objects[0].lum_mds = mdt_index;
+		tmp->lum_objects[0].lum_fid = *ll_inode2fid(inode);
+		for (i = 1; i < stripe_count; i++) {
+			struct lmv_mds_md_v1 *lmm1;
+
+			lmm1 = &lmm->lmv_md_v1;
+			mdt_index = ll_get_mdt_idx_by_fid(sbi,
+							  &lmm1->lmv_stripe_fids[i]);
+			if (mdt_index < 0) {
+				rc = mdt_index;
+				goto out_tmp;
+			}
+			tmp->lum_objects[i].lum_mds = mdt_index;
+			tmp->lum_objects[i].lum_fid = lmm1->lmv_stripe_fids[i];
+			tmp->lum_stripe_count++;
 		}
 
-		tmp->lum_stripe_offset = mdtindex;
-		tmp->lum_objects[0].lum_mds = mdtindex;
-		memcpy(&tmp->lum_objects[0].lum_fid, ll_inode2fid(inode),
-		       sizeof(struct lu_fid));
-		if (copy_to_user((void __user *)arg, tmp, lum_size)) {
+		if (copy_to_user(ulmv, tmp, lum_size)) {
 			rc = -EFAULT;
-			goto free_lmv;
+			goto out_tmp;
 		}
-free_lmv:
+out_tmp:
 		kfree(tmp);
+finish_req:
+		ptlrpc_req_finished(request);
 		return rc;
 	}
+
 	case LL_IOC_LOV_SWAP_LAYOUTS:
 		return -EPERM;
 	case LL_IOC_OBD_STATFS:
@@ -1484,7 +1585,8 @@ free_lmv:
 			rc = ll_lov_getstripe_ea_info(inode, filename, &lmm,
 						      &lmmsize, &request);
 		} else {
-			rc = ll_dir_getstripe(inode, &lmm, &lmmsize, &request);
+			rc = ll_dir_getstripe(inode, (void **)&lmm, &lmmsize,
+					      &request, 0);
 		}
 
 		if (request) {
diff --git a/drivers/staging/lustre/lustre/llite/llite_internal.h b/drivers/staging/lustre/lustre/llite/llite_internal.h
index f3b8504..82c3a88 100644
--- a/drivers/staging/lustre/lustre/llite/llite_internal.h
+++ b/drivers/staging/lustre/lustre/llite/llite_internal.h
@@ -728,8 +728,8 @@ int ll_lov_getstripe_ea_info(struct inode *inode, const char *filename,
 			     struct ptlrpc_request **request);
 int ll_dir_setstripe(struct inode *inode, struct lov_user_md *lump,
 		     int set_default);
-int ll_dir_getstripe(struct inode *inode, struct lov_mds_md **lmmp,
-		     int *lmm_size, struct ptlrpc_request **request);
+int ll_dir_getstripe(struct inode *inode, void **lmmp, int *lmm_size,
+		     struct ptlrpc_request **request, u64 valid);
 int ll_fsync(struct file *file, loff_t start, loff_t end, int data);
 int ll_merge_attr(const struct lu_env *env, struct inode *inode);
 int ll_fid2path(struct inode *inode, void __user *arg);
diff --git a/drivers/staging/lustre/lustre/llite/xattr.c b/drivers/staging/lustre/lustre/llite/xattr.c
index a02b802..aa0738b 100644
--- a/drivers/staging/lustre/lustre/llite/xattr.c
+++ b/drivers/staging/lustre/lustre/llite/xattr.c
@@ -390,8 +390,8 @@ static int ll_xattr_get(const struct xattr_handler *handler,
 		lsm = ccc_inode_lsm_get(inode);
 		if (!lsm) {
 			if (S_ISDIR(inode->i_mode)) {
-				rc = ll_dir_getstripe(inode, &lmm,
-						      &lmmsize, &request);
+				rc = ll_dir_getstripe(inode, (void **)&lmm,
+						      &lmmsize, &request, 0);
 			} else {
 				rc = -ENODATA;
 			}
@@ -491,7 +491,8 @@ ssize_t ll_listxattr(struct dentry *dentry, char *buffer, size_t size)
 		if (!ll_i2info(inode)->lli_has_smd)
 			rc2 = -1;
 	} else if (S_ISDIR(inode->i_mode)) {
-		rc2 = ll_dir_getstripe(inode, &lmm, &lmmsize, &request);
+		rc2 = ll_dir_getstripe(inode, (void **)&lmm, &lmmsize,
+				       &request, 0);
 	}
 
 	if (rc2 < 0) {
diff --git a/drivers/staging/lustre/lustre/ptlrpc/pack_generic.c b/drivers/staging/lustre/lustre/ptlrpc/pack_generic.c
index 07e23d1..6ddc9c7 100644
--- a/drivers/staging/lustre/lustre/ptlrpc/pack_generic.c
+++ b/drivers/staging/lustre/lustre/ptlrpc/pack_generic.c
@@ -1878,6 +1878,32 @@ void lustre_swab_lov_desc(struct lov_desc *ld)
 }
 EXPORT_SYMBOL(lustre_swab_lov_desc);
 
+/* This structure is always in little-endian */
+static void lustre_swab_lmv_mds_md_v1(struct lmv_mds_md_v1 *lmm1)
+{
+	int i;
+
+	__swab32s(&lmm1->lmv_magic);
+	__swab32s(&lmm1->lmv_stripe_count);
+	__swab32s(&lmm1->lmv_master_mdt_index);
+	__swab32s(&lmm1->lmv_hash_type);
+	__swab32s(&lmm1->lmv_layout_version);
+	for (i = 0; i < lmm1->lmv_stripe_count; i++)
+		lustre_swab_lu_fid(&lmm1->lmv_stripe_fids[i]);
+}
+
+void lustre_swab_lmv_mds_md(union lmv_mds_md *lmm)
+{
+	switch (lmm->lmv_magic) {
+	case LMV_MAGIC_V1:
+		lustre_swab_lmv_mds_md_v1(&lmm->lmv_md_v1);
+		break;
+	default:
+		break;
+	}
+}
+EXPORT_SYMBOL(lustre_swab_lmv_mds_md);
+
 void lustre_swab_lmv_user_md(struct lmv_user_md *lum)
 {
 	__swab32s(&lum->lum_magic);
-- 
1.7.1

[PATCH 32/58] staging: lustre: delete striped directory

[James Simmons]

From: wang di <di.wang@intel.com>

Add delete striped directory, it includes

1. enable sync log between MDTs, so slave objects will
   be delete by unlink log, which is similar as deleting ost
   object.

2. retrieve layout information of striped directory on MDT,
   then lock all of the slave objects before unlink.

Signed-off-by: wang di <di.wang@intel.com>
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-3531
Reviewed-on: http://review.whamcloud.com/7445
Reviewed-by: Alex Zhuravlev <alexey.zhuravlev@intel.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
Signed-off-by: James Simmons <jsimmons@infradead.org>
---
 drivers/staging/lustre/lustre/include/lustre_dlm.h |    1 +
 drivers/staging/lustre/lustre/include/lustre_fid.h |    1 +
 drivers/staging/lustre/lustre/llite/dir.c          |   10 ---
 drivers/staging/lustre/lustre/lmv/lmv_intent.c     |    5 ++
 drivers/staging/lustre/lustre/lmv/lmv_obd.c        |   75 +++++++++++++++-----
 5 files changed, 65 insertions(+), 27 deletions(-)

diff --git a/drivers/staging/lustre/lustre/include/lustre_dlm.h b/drivers/staging/lustre/lustre/include/lustre_dlm.h
index 60051a5..f7805cc 100644
--- a/drivers/staging/lustre/lustre/include/lustre_dlm.h
+++ b/drivers/staging/lustre/lustre/include/lustre_dlm.h
@@ -968,6 +968,7 @@ struct ldlm_enqueue_info {
 	void *ei_cb_cp;  /** lock completion callback */
 	void *ei_cb_gl;  /** lock glimpse callback */
 	void *ei_cbdata; /** Data to be passed into callbacks. */
+	unsigned int ei_enq_slave:1; /* whether enqueue slave stripes */
 };
 
 extern struct obd_ops ldlm_obd_ops;
diff --git a/drivers/staging/lustre/lustre/include/lustre_fid.h b/drivers/staging/lustre/lustre/include/lustre_fid.h
index 743671a..61f3930 100644
--- a/drivers/staging/lustre/lustre/include/lustre_fid.h
+++ b/drivers/staging/lustre/lustre/include/lustre_fid.h
@@ -229,6 +229,7 @@ enum local_oid {
 	MDD_LOV_OBJ_OSEQ	= 4121UL,
 	LFSCK_NAMESPACE_OID     = 4122UL,
 	REMOTE_PARENT_DIR_OID	= 4123UL,
+	SLAVE_LLOG_CATALOGS_OID	= 4124UL,
 };
 
 static inline void lu_local_obj_fid(struct lu_fid *fid, __u32 oid)
diff --git a/drivers/staging/lustre/lustre/llite/dir.c b/drivers/staging/lustre/lustre/llite/dir.c
index 5288750..96ae7d5 100644
--- a/drivers/staging/lustre/lustre/llite/dir.c
+++ b/drivers/staging/lustre/lustre/llite/dir.c
@@ -679,16 +679,6 @@ static int ll_dir_setdirstripe(struct inode *dir, struct lmv_user_md *lump,
 	if (unlikely(lump->lum_magic != LMV_USER_MAGIC))
 		return -EINVAL;
 
-	if (lump->lum_stripe_offset == (__u32)-1) {
-		int mdtidx;
-
-		mdtidx = ll_get_mdt_idx(dir);
-		if (mdtidx < 0)
-			return mdtidx;
-
-		lump->lum_stripe_offset = mdtidx;
-	}
-
 	CDEBUG(D_VFSTRACE, "VFS Op:inode="DFID"(%p) name %s stripe_offset %d, stripe_count: %u\n",
 	       PFID(ll_inode2fid(dir)), dir, filename,
 	       (int)lump->lum_stripe_offset, lump->lum_stripe_count);
diff --git a/drivers/staging/lustre/lustre/lmv/lmv_intent.c b/drivers/staging/lustre/lustre/lmv/lmv_intent.c
index 1b9bbb2..5313dfc 100644
--- a/drivers/staging/lustre/lustre/lmv/lmv_intent.c
+++ b/drivers/staging/lustre/lustre/lmv/lmv_intent.c
@@ -244,6 +244,11 @@ update:
 				if (req)
 					ptlrpc_req_finished(req);
 
+				if (it.it_lock_mode && lockh) {
+					ldlm_lock_decref(lockh, it.it_lock_mode);
+					it.it_lock_mode = 0;
+				}
+
 				rc = -EIO;
 				goto cleanup;
 			}
diff --git a/drivers/staging/lustre/lustre/lmv/lmv_obd.c b/drivers/staging/lustre/lustre/lmv/lmv_obd.c
index df29ad5..4995735 100644
--- a/drivers/staging/lustre/lustre/lmv/lmv_obd.c
+++ b/drivers/staging/lustre/lustre/lmv/lmv_obd.c
@@ -103,6 +103,9 @@ int lmv_name_to_stripe_index(enum lmv_hash_type hashtype,
 		return -EINVAL;
 	}
 
+	CDEBUG(D_INFO, "name %.*s hash_type %d idx %d\n", namelen, name,
+	       hashtype, idx);
+
 	LASSERT(idx < max_mdt_index);
 	return idx;
 }
@@ -1232,7 +1235,16 @@ static int lmv_placement_policy(struct obd_device *obd,
 		struct lmv_user_md *lum;
 
 		lum = op_data->op_data;
-		*mds = lum->lum_stripe_offset;
+		if (lum->lum_stripe_offset != (__u32)-1) {
+			*mds = lum->lum_stripe_offset;
+		} else {
+			/*
+			 * -1 means default, which will be in the same MDT with
+			 * the stripe
+			 */
+			*mds = op_data->op_mds;
+			lum->lum_stripe_offset = op_data->op_mds;
+		}
 	} else {
 		/*
 		 * Allocate new fid on target according to operation type and
@@ -1648,12 +1660,28 @@ static int lmv_close(struct obd_export *exp, struct md_op_data *op_data,
  * For striped-directory, it will locate MDT by name. And also
  * it will reset op_fid1 with the FID of the chosen stripe.
  **/
+struct lmv_tgt_desc *
+lmv_locate_target_for_name(struct lmv_obd *lmv, struct lmv_stripe_md *lsm,
+			   const char *name, int namelen, struct lu_fid *fid,
+			   u32 *mds)
+{
+	const struct lmv_oinfo *oinfo;
+	struct lmv_tgt_desc *tgt;
+
+	oinfo = lsm_name_to_stripe_info(lsm, name, namelen);
+	*fid = oinfo->lmo_fid;
+	*mds = oinfo->lmo_mds;
+	tgt = lmv_get_target(lmv, *mds);
+
+	CDEBUG(D_INFO, "locate on mds %u "DFID"\n", *mds, PFID(fid));
+	return tgt;
+}
+
 struct lmv_tgt_desc
 *lmv_locate_mds(struct lmv_obd *lmv, struct md_op_data *op_data,
 		struct lu_fid *fid)
 {
 	struct lmv_stripe_md *lsm = op_data->op_mea1;
-	const struct lmv_oinfo *oinfo;
 	struct lmv_tgt_desc *tgt;
 
 	if (!lsm || lsm->lsm_md_stripe_count <= 1 ||
@@ -1667,15 +1695,9 @@ struct lmv_tgt_desc
 		return tgt;
 	}
 
-	oinfo = lsm_name_to_stripe_info(lsm, op_data->op_name,
-					op_data->op_namelen);
-	*fid = oinfo->lmo_fid;
-	op_data->op_mds = oinfo->lmo_mds;
-	tgt = lmv_get_target(lmv, op_data->op_mds);
-
-	CDEBUG(D_INFO, "locate on mds %u\n", op_data->op_mds);
-
-	return tgt;
+	return lmv_locate_target_for_name(lmv, lsm, op_data->op_name,
+					  op_data->op_namelen, fid,
+					  &op_data->op_mds);
 }
 
 static int lmv_create(struct obd_export *exp, struct md_op_data *op_data,
@@ -2077,6 +2099,9 @@ static int lmv_rename(struct obd_export *exp, struct md_op_data *op_data,
 				      LCK_EX, MDS_INODELOCK_FULL,
 				      MF_MDC_CANCEL_FID4);
 
+	CDEBUG(D_INODE, DFID":m%d to "DFID"\n", PFID(&op_data->op_fid1),
+	       op_data->op_mds, PFID(&op_data->op_fid2));
+
 	if (rc == 0)
 		rc = md_rename(src_tgt->ltd_exp, op_data, old, oldlen,
 			       new, newlen, request);
@@ -2290,12 +2315,26 @@ static int lmv_unlink(struct obd_export *exp, struct md_op_data *op_data,
 		return rc;
 retry:
 	/* Send unlink requests to the MDT where the child is located */
-	if (likely(!fid_is_zero(&op_data->op_fid2)))
-		tgt = lmv_locate_mds(lmv, op_data, &op_data->op_fid2);
-	else
+	if (likely(!fid_is_zero(&op_data->op_fid2))) {
+		tgt = lmv_find_target(lmv, &op_data->op_fid2);
+		if (IS_ERR(tgt))
+			return PTR_ERR(tgt);
+
+		/* For striped dir, we need to locate the parent as well */
+		if (op_data->op_mea1 &&
+		    op_data->op_mea1->lsm_md_stripe_count > 1) {
+			LASSERT(op_data->op_name && op_data->op_namelen);
+			lmv_locate_target_for_name(lmv, op_data->op_mea1,
+						   op_data->op_name,
+						   op_data->op_namelen,
+						   &op_data->op_fid1,
+						   &op_data->op_mds);
+		}
+	} else {
 		tgt = lmv_locate_mds(lmv, op_data, &op_data->op_fid1);
-	if (IS_ERR(tgt))
-		return PTR_ERR(tgt);
+		if (IS_ERR(tgt))
+			return PTR_ERR(tgt);
+	}
 
 	op_data->op_fsuid = from_kuid(&init_user_ns, current_fsuid());
 	op_data->op_fsgid = from_kgid(&init_user_ns, current_fsgid());
@@ -2801,8 +2840,10 @@ static int lmv_free_lustre_md(struct obd_export *exp, struct lustre_md *md)
 	struct lmv_obd	  *lmv = &obd->u.lmv;
 	struct lmv_tgt_desc *tgt = lmv->tgts[0];
 
-	if (md->lmv)
+	if (md->lmv) {
 		lmv_free_memmd(md->lmv);
+		md->lmv = NULL;
+	}
 	if (!tgt || !tgt->ltd_exp)
 		return -EINVAL;
 	return md_free_lustre_md(tgt->ltd_exp, md);
-- 
1.7.1

[PATCH 33/58] staging: lustre: obdclass: fix lmd_parse() to handle comma-separated NIDs

[James Simmons]

From: Jian Yu <jian.yu@intel.com>

This patch handles the  upgrade situation that old mountdata already
contains comma-separated NIDs. The correct way to fix the original
issue is to parse comma-separated NIDs in lmd_parse().

Signed-off-by: Jian Yu <jian.yu@intel.com>
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-4460
Reviewed-on: http://review.whamcloud.com/8918
Reviewed-by: Niu Yawei <yawei.niu@intel.com>
Reviewed-by: Bobi Jam <bobijam@gmail.com>
Reviewed-by: Sebastien Buisson <sebastien.buisson@bull.net>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
Signed-off-by: James Simmons <jsimmons@infradead.org>
---
 drivers/staging/lustre/lustre/obdclass/obd_mount.c |   20 ++++++++++++++++----
 1 files changed, 16 insertions(+), 4 deletions(-)

diff --git a/drivers/staging/lustre/lustre/obdclass/obd_mount.c b/drivers/staging/lustre/lustre/obdclass/obd_mount.c
index aa84a50..4931e37 100644
--- a/drivers/staging/lustre/lustre/obdclass/obd_mount.c
+++ b/drivers/staging/lustre/lustre/obdclass/obd_mount.c
@@ -880,7 +880,7 @@ static int lmd_parse_mgs(struct lustre_mount_data *lmd, char **ptr)
  */
 static int lmd_parse(char *options, struct lustre_mount_data *lmd)
 {
-	char *s1, *s2, *devname = NULL;
+	char *s1, *s2, *s3, *devname = NULL;
 	struct lustre_mount_data *raw = (struct lustre_mount_data *)options;
 	int rc = 0;
 
@@ -913,6 +913,7 @@ static int lmd_parse(char *options, struct lustre_mount_data *lmd)
 		/* Skip whitespace and extra commas */
 		while (*s1 == ' ' || *s1 == ',')
 			s1++;
+		s3 = s1;
 
 		/* Client options are parsed in ll_options: eg. flock,
 		 * user_xattr, acl
@@ -970,6 +971,7 @@ static int lmd_parse(char *options, struct lustre_mount_data *lmd)
 			rc = lmd_parse_mgssec(lmd, s1 + 7);
 			if (rc)
 				goto invalid;
+			s3 = s2;
 			clear++;
 		/* ost exclusion list */
 		} else if (strncmp(s1, "exclude=", 8) == 0) {
@@ -990,10 +992,19 @@ static int lmd_parse(char *options, struct lustre_mount_data *lmd)
 			size_t length, params_length;
 			char *tail = strchr(s1 + 6, ',');
 
-			if (!tail)
+			if (!tail) {
 				length = strlen(s1);
-			else
-				length = tail - s1;
+			} else {
+				lnet_nid_t nid;
+				char *param_str = tail + 1;
+				int supplementary = 1;
+
+				while (!class_parse_nid_quiet(param_str, &nid,
+							      &param_str)) {
+					supplementary = 0;
+				}
+				length = param_str - s1 - supplementary;
+			}
 			length -= 6;
 			params_length = strlen(lmd->lmd_params);
 			if (params_length + length + 1 >= LMD_PARAMS_MAXLEN)
@@ -1001,6 +1012,7 @@ static int lmd_parse(char *options, struct lustre_mount_data *lmd)
 			strncat(lmd->lmd_params, s1 + 6, length);
 			lmd->lmd_params[params_length + length] = '\0';
 			strlcat(lmd->lmd_params, " ", LMD_PARAMS_MAXLEN);
+			s3 = s1 + 6 + length;
 			clear++;
 		} else if (strncmp(s1, "osd=", 4) == 0) {
 			rc = lmd_parse_string(&lmd->lmd_osd_type, s1 + 4);
-- 
1.7.1

[PATCH 34/58] staging: lustre: obdclass: bug fixes for lu_device_type handling

[James Simmons]

From: Fan Yong <fan.yong@intel.com>

There was no protection when inc/dec lu_device_type::ldt_device_nr,
which may caused the ldt_device_nr to be wrong and trigger assert.
This patch redefine lu_device_type::ldt_device_nr as atomic type.

There was no protection when add/del lu_device_type::ldt_linkage
into/from the global lu_device_types list, which may caused bad
address accessing. This patch uses the existing obd_types_lock
to protect related operations.

We do NOT need lu_types_stop() any longer. Such function scans
the global lu_device_types list, and for each type item on it
which has zerod lu_device_type::ldt_device_nr, call its stop()
method. In fact, the lu_device_type::ldt_device_nr only will be
zero when the last lu_device_fini() is called, and at that time,
inside the lu_device_fini(), its stop() method will be called.
So it is unnecessary to call the stop() again via lu_types_stop().

Signed-off-by: Fan Yong <fan.yong@intel.com>
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-4604
Reviewed-on: http://review.whamcloud.com/8694
Reviewed-by: Jian Yu <jian.yu@intel.com>
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
Signed-off-by: James Simmons <jsimmons@infradead.org>
---
 drivers/staging/lustre/lustre/include/lu_object.h  |    3 +-
 drivers/staging/lustre/lustre/llite/vvp_dev.c      |    6 ---
 drivers/staging/lustre/lustre/obdclass/lu_object.c |   34 ++++++++++----------
 drivers/staging/lustre/lustre/obdclass/obd_mount.c |    1 -
 4 files changed, 18 insertions(+), 26 deletions(-)

diff --git a/drivers/staging/lustre/lustre/include/lu_object.h b/drivers/staging/lustre/lustre/include/lu_object.h
index 6e25c1b..25c12d8 100644
--- a/drivers/staging/lustre/lustre/include/lu_object.h
+++ b/drivers/staging/lustre/lustre/include/lu_object.h
@@ -327,7 +327,7 @@ struct lu_device_type {
 	/**
 	 * Number of existing device type instances.
 	 */
-	unsigned				ldt_device_nr;
+	atomic_t				ldt_device_nr;
 	/**
 	 * Linkage into a global list of all device types.
 	 *
@@ -673,7 +673,6 @@ void lu_object_add(struct lu_object *before, struct lu_object *o);
 
 int  lu_device_type_init(struct lu_device_type *ldt);
 void lu_device_type_fini(struct lu_device_type *ldt);
-void lu_types_stop(void);
 
 /** @} ctors */
 
diff --git a/drivers/staging/lustre/lustre/llite/vvp_dev.c b/drivers/staging/lustre/lustre/llite/vvp_dev.c
index e623216..771c0bd 100644
--- a/drivers/staging/lustre/lustre/llite/vvp_dev.c
+++ b/drivers/staging/lustre/lustre/llite/vvp_dev.c
@@ -368,12 +368,6 @@ int cl_sb_fini(struct super_block *sb)
 		CERROR("Cannot cleanup cl-stack due to memory shortage.\n");
 		result = PTR_ERR(env);
 	}
-	/*
-	 * If mount failed (sbi->ll_cl == NULL), and this there are no other
-	 * mounts, stop device types manually (this usually happens
-	 * automatically when last device is destroyed).
-	 */
-	lu_types_stop();
 	return result;
 }
 
diff --git a/drivers/staging/lustre/lustre/obdclass/lu_object.c b/drivers/staging/lustre/lustre/obdclass/lu_object.c
index 9b03059..0c00bf8 100644
--- a/drivers/staging/lustre/lustre/obdclass/lu_object.c
+++ b/drivers/staging/lustre/lustre/obdclass/lu_object.c
@@ -726,34 +726,31 @@ int lu_device_type_init(struct lu_device_type *ldt)
 {
 	int result = 0;
 
+	atomic_set(&ldt->ldt_device_nr, 0);
 	INIT_LIST_HEAD(&ldt->ldt_linkage);
 	if (ldt->ldt_ops->ldto_init)
 		result = ldt->ldt_ops->ldto_init(ldt);
-	if (result == 0)
+
+	if (!result) {
+		spin_lock(&obd_types_lock);
 		list_add(&ldt->ldt_linkage, &lu_device_types);
+		spin_unlock(&obd_types_lock);
+	}
+
 	return result;
 }
 EXPORT_SYMBOL(lu_device_type_init);
 
 void lu_device_type_fini(struct lu_device_type *ldt)
 {
+	spin_lock(&obd_types_lock);
 	list_del_init(&ldt->ldt_linkage);
+	spin_unlock(&obd_types_lock);
 	if (ldt->ldt_ops->ldto_fini)
 		ldt->ldt_ops->ldto_fini(ldt);
 }
 EXPORT_SYMBOL(lu_device_type_fini);
 
-void lu_types_stop(void)
-{
-	struct lu_device_type *ldt;
-
-	list_for_each_entry(ldt, &lu_device_types, ldt_linkage) {
-		if (ldt->ldt_device_nr == 0 && ldt->ldt_ops->ldto_stop)
-			ldt->ldt_ops->ldto_stop(ldt);
-	}
-}
-EXPORT_SYMBOL(lu_types_stop);
-
 /**
  * Global list of all sites on this node
  */
@@ -1082,8 +1079,10 @@ EXPORT_SYMBOL(lu_device_put);
  */
 int lu_device_init(struct lu_device *d, struct lu_device_type *t)
 {
-	if (t->ldt_device_nr++ == 0 && t->ldt_ops->ldto_start)
+	if (atomic_inc_return(&t->ldt_device_nr) == 1 &&
+	    t->ldt_ops->ldto_start)
 		t->ldt_ops->ldto_start(t);
+
 	memset(d, 0, sizeof(*d));
 	atomic_set(&d->ld_ref, 0);
 	d->ld_type = t;
@@ -1098,9 +1097,8 @@ EXPORT_SYMBOL(lu_device_init);
  */
 void lu_device_fini(struct lu_device *d)
 {
-	struct lu_device_type *t;
+	struct lu_device_type *t = d->ld_type;
 
-	t = d->ld_type;
 	if (d->ld_obd) {
 		d->ld_obd->obd_lu_dev = NULL;
 		d->ld_obd = NULL;
@@ -1109,8 +1107,10 @@ void lu_device_fini(struct lu_device *d)
 	lu_ref_fini(&d->ld_reference);
 	LASSERTF(atomic_read(&d->ld_ref) == 0,
 		 "Refcount is %u\n", atomic_read(&d->ld_ref));
-	LASSERT(t->ldt_device_nr > 0);
-	if (--t->ldt_device_nr == 0 && t->ldt_ops->ldto_stop)
+	LASSERT(atomic_read(&t->ldt_device_nr) > 0);
+
+	if (atomic_dec_and_test(&t->ldt_device_nr) &&
+	    t->ldt_ops->ldto_stop)
 		t->ldt_ops->ldto_stop(t);
 }
 EXPORT_SYMBOL(lu_device_fini);
diff --git a/drivers/staging/lustre/lustre/obdclass/obd_mount.c b/drivers/staging/lustre/lustre/obdclass/obd_mount.c
index 4931e37..33d6c42 100644
--- a/drivers/staging/lustre/lustre/obdclass/obd_mount.c
+++ b/drivers/staging/lustre/lustre/obdclass/obd_mount.c
@@ -670,7 +670,6 @@ int lustre_common_put_super(struct super_block *sb)
 	}
 	/* Drop a ref to the mounted disk */
 	lustre_put_lsi(sb);
-	lu_types_stop();
 	return rc;
 }
 EXPORT_SYMBOL(lustre_common_put_super);
-- 
1.7.1

[PATCH 35/58] staging: lustre: add ability to migrate inodes.

[James Simmons]

From: wang di <di.wang@intel.com>

Add client support to migrate the individual inodes
from one MDT to another MDT, and this functionality
will only migrate inode layout on MDT but not touch
data object on OST.

The directory will be migrated from top to the bottom,
i.e. migrating parent first, then migrating the child.

Signed-off-by: wang di <di.wang@intel.com>
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-2430
Reviewed-on: http://review.whamcloud.com/6662
Reviewed-by: Alex Zhuravlev <alexey.zhuravlev@intel.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
Signed-off-by: James Simmons <jsimmons@infradead.org>
---
 .../lustre/lustre/include/lustre/lustre_idl.h      |   11 +-
 .../lustre/lustre/include/lustre/lustre_user.h     |    1 +
 drivers/staging/lustre/lustre/include/lustre_lmv.h |    2 +
 drivers/staging/lustre/lustre/include/obd.h        |   12 +--
 drivers/staging/lustre/lustre/llite/dir.c          |   43 +++++-
 drivers/staging/lustre/lustre/llite/file.c         |  113 ++++++++++++-
 .../staging/lustre/lustre/llite/llite_internal.h   |   14 ++-
 drivers/staging/lustre/lustre/llite/llite_lib.c    |   33 ++++-
 drivers/staging/lustre/lustre/llite/namei.c        |    3 +-
 drivers/staging/lustre/lustre/llite/rw.c           |    4 +
 drivers/staging/lustre/lustre/llite/statahead.c    |    1 +
 drivers/staging/lustre/lustre/lmv/lmv_intent.c     |   32 +++-
 drivers/staging/lustre/lustre/lmv/lmv_obd.c        |  176 ++++++++++++++------
 drivers/staging/lustre/lustre/mdc/mdc_lib.c        |    2 +
 drivers/staging/lustre/lustre/ptlrpc/wiretest.c    |    4 +-
 15 files changed, 368 insertions(+), 83 deletions(-)

diff --git a/drivers/staging/lustre/lustre/include/lustre/lustre_idl.h b/drivers/staging/lustre/lustre/include/lustre/lustre_idl.h
index 0ff30c6..6853f62 100644
--- a/drivers/staging/lustre/lustre/include/lustre/lustre_idl.h
+++ b/drivers/staging/lustre/lustre/include/lustre/lustre_idl.h
@@ -1482,6 +1482,7 @@ enum obdo_flags {
 #define LOV_MAGIC	 LOV_MAGIC_V1
 #define LOV_MAGIC_JOIN_V1 0x0BD20BD0
 #define LOV_MAGIC_V3      0x0BD30BD0
+#define LOV_MAGIC_MIGRATE 0x0BD40BD0
 
 /*
  * magic for fully defined striping
@@ -1987,7 +1988,7 @@ enum mdt_reint_cmd {
 	REINT_OPEN     = 6,
 	REINT_SETXATTR = 7,
 	REINT_RMENTRY  = 8,
-/*      REINT_WRITE    = 9, */
+	REINT_MIGRATE  = 9,
 	REINT_MAX
 };
 
@@ -2280,6 +2281,7 @@ enum mds_op_bias {
 	MDS_CREATE_VOLATILE	= 1 << 10,
 	MDS_OWNEROVERRIDE	= 1 << 11,
 	MDS_HSM_RELEASE		= 1 << 12,
+	MDS_RENAME_MIGRATE	= BIT(13),
 };
 
 /* instance of mdt_reint_rec */
@@ -2488,11 +2490,13 @@ struct lmv_desc {
 /* lmv structures */
 #define LMV_MAGIC_V1	0x0CD10CD0	/* normal stripe lmv magic */
 #define LMV_USER_MAGIC	0x0CD20CD0	/* default lmv magic*/
+#define LMV_MAGIC_MIGRATE	0x0CD30CD0	/* migrate stripe lmv magic */
 #define LMV_MAGIC	LMV_MAGIC_V1
 
 enum lmv_hash_type {
 	LMV_HASH_TYPE_ALL_CHARS = 1,
 	LMV_HASH_TYPE_FNV_1A_64 = 2,
+	LMV_HASH_TYPE_MIGRATION = 3,
 };
 
 #define LMV_HASH_NAME_ALL_CHARS		"all_char"
@@ -2552,7 +2556,8 @@ static inline ssize_t lmv_mds_md_size(int stripe_count, unsigned int lmm_magic)
 	ssize_t len = -EINVAL;
 
 	switch (lmm_magic) {
-	case LMV_MAGIC_V1: {
+	case LMV_MAGIC_V1:
+	case LMV_MAGIC_MIGRATE: {
 		struct lmv_mds_md_v1 *lmm1;
 
 		len = sizeof(*lmm1);
@@ -2568,6 +2573,7 @@ static inline int lmv_mds_md_stripe_count_get(const union lmv_mds_md *lmm)
 {
 	switch (le32_to_cpu(lmm->lmv_magic)) {
 	case LMV_MAGIC_V1:
+	case LMV_MAGIC_MIGRATE:
 		return le32_to_cpu(lmm->lmv_md_v1.lmv_stripe_count);
 	case LMV_USER_MAGIC:
 		return le32_to_cpu(lmm->lmv_user_md.lum_stripe_count);
@@ -2583,6 +2589,7 @@ static inline int lmv_mds_md_stripe_count_set(union lmv_mds_md *lmm,
 
 	switch (le32_to_cpu(lmm->lmv_magic)) {
 	case LMV_MAGIC_V1:
+	case LMV_MAGIC_MIGRATE:
 		lmm->lmv_md_v1.lmv_stripe_count = cpu_to_le32(stripe_count);
 		break;
 	case LMV_USER_MAGIC:
diff --git a/drivers/staging/lustre/lustre/include/lustre/lustre_user.h b/drivers/staging/lustre/lustre/include/lustre/lustre_user.h
index 26dbda0..4746320 100644
--- a/drivers/staging/lustre/lustre/include/lustre/lustre_user.h
+++ b/drivers/staging/lustre/lustre/include/lustre/lustre_user.h
@@ -243,6 +243,7 @@ struct ost_id {
 #define LL_IOC_GET_LEASE		_IO('f', 244)
 #define LL_IOC_HSM_IMPORT		_IOWR('f', 245, struct hsm_user_import)
 #define LL_IOC_LMV_SET_DEFAULT_STRIPE	_IOWR('f', 246, struct lmv_user_md)
+#define LL_IOC_MIGRATE			_IOR('f', 247, int)
 
 #define LL_STATFS_LMV	   1
 #define LL_STATFS_LOV	   2
diff --git a/drivers/staging/lustre/lustre/include/lustre_lmv.h b/drivers/staging/lustre/lustre/include/lustre_lmv.h
index 4036fce..feee981 100644
--- a/drivers/staging/lustre/lustre/include/lustre_lmv.h
+++ b/drivers/staging/lustre/lustre/include/lustre_lmv.h
@@ -106,6 +106,7 @@ static inline void lmv_cpu_to_le(union lmv_mds_md *lmv_dst,
 {
 	switch (lmv_src->lmv_magic) {
 	case LMV_MAGIC_V1:
+	case LMV_MAGIC_MIGRATE:
 		lmv1_cpu_to_le(&lmv_dst->lmv_md_v1, &lmv_src->lmv_md_v1);
 		break;
 	default:
@@ -118,6 +119,7 @@ static inline void lmv_le_to_cpu(union lmv_mds_md *lmv_dst,
 {
 	switch (le32_to_cpu(lmv_src->lmv_magic)) {
 	case LMV_MAGIC_V1:
+	case LMV_MAGIC_MIGRATE:
 		lmv1_le_to_cpu(&lmv_dst->lmv_md_v1, &lmv_src->lmv_md_v1);
 		break;
 	default:
diff --git a/drivers/staging/lustre/lustre/include/obd.h b/drivers/staging/lustre/lustre/include/obd.h
index a9f4e13..f5eeb05 100644
--- a/drivers/staging/lustre/lustre/include/obd.h
+++ b/drivers/staging/lustre/lustre/include/obd.h
@@ -847,9 +847,6 @@ struct md_op_data {
 	/* Various operation flags. */
 	enum mds_op_bias        op_bias;
 
-	/* Operation type */
-	__u32		   op_opc;
-
 	/* Used by readdir */
 	__u64		   op_offset;
 
@@ -871,6 +868,7 @@ enum op_cli_flags {
 	CLI_RM_ENTRY	= 1 << 1,
 	CLI_HASH64	= BIT(2),
 	CLI_API32	= BIT(3),
+	CLI_MIGRATE	= BIT(4),
 };
 
 struct md_enqueue_info;
@@ -1013,14 +1011,6 @@ struct obd_ops {
 	 */
 };
 
-enum {
-	LUSTRE_OPC_MKDIR    = (1 << 0),
-	LUSTRE_OPC_SYMLINK  = (1 << 1),
-	LUSTRE_OPC_MKNOD    = (1 << 2),
-	LUSTRE_OPC_CREATE   = (1 << 3),
-	LUSTRE_OPC_ANY      = (1 << 4)
-};
-
 /* lmv structures */
 struct lustre_md {
 	struct mdt_body	 *body;
diff --git a/drivers/staging/lustre/lustre/llite/dir.c b/drivers/staging/lustre/lustre/llite/dir.c
index 96ae7d5..ef7322e 100644
--- a/drivers/staging/lustre/lustre/llite/dir.c
+++ b/drivers/staging/lustre/lustre/llite/dir.c
@@ -883,6 +883,7 @@ int ll_dir_getstripe(struct inode *inode, void **plmm, int *plmm_size,
 			lustre_swab_lov_user_md_v3((struct lov_user_md_v3 *)lmm);
 		break;
 	case LMV_USER_MAGIC:
+	case LMV_MAGIC_MIGRATE:
 		if (cpu_to_le32(LMV_USER_MAGIC) != LMV_USER_MAGIC)
 			lustre_swab_lmv_user_md((struct lmv_user_md *)lmm);
 		break;
@@ -897,8 +898,7 @@ out:
 	return rc;
 }
 
-static int ll_get_mdt_idx_by_fid(struct ll_sb_info *sbi,
-				 const struct lu_fid *fid)
+int ll_get_mdt_idx_by_fid(struct ll_sb_info *sbi, const struct lu_fid *fid)
 {
 	struct md_op_data *op_data;
 	int mdt_index, rc;
@@ -1960,6 +1960,45 @@ out_quotactl:
 		kfree(copy);
 		return rc;
 	}
+	case LL_IOC_MIGRATE: {
+		char *buf = NULL;
+		const char *filename;
+		int namelen = 0;
+		int len;
+		int rc;
+		int mdtidx;
+
+		rc = obd_ioctl_getdata(&buf, &len, (void __user *)arg);
+		if (rc < 0)
+			return rc;
+
+		data = (struct obd_ioctl_data *)buf;
+		if (!data->ioc_inlbuf1 || !data->ioc_inlbuf2 ||
+		    !data->ioc_inllen1 || !data->ioc_inllen2) {
+			rc = -EINVAL;
+			goto migrate_free;
+		}
+
+		filename = data->ioc_inlbuf1;
+		namelen = data->ioc_inllen1;
+		if (namelen < 1) {
+			rc = -EINVAL;
+			goto migrate_free;
+		}
+
+		if (data->ioc_inllen2 != sizeof(mdtidx)) {
+			rc = -EINVAL;
+			goto migrate_free;
+		}
+		mdtidx = *(int *)data->ioc_inlbuf2;
+
+		rc = ll_migrate(inode, file, mdtidx, filename, namelen);
+migrate_free:
+		obd_ioctl_freedata(buf, len);
+
+		return rc;
+	}
+
 	default:
 		return obd_iocontrol(cmd, sbi->ll_dt_exp, 0, NULL,
 				     (void __user *)arg);
diff --git a/drivers/staging/lustre/lustre/llite/file.c b/drivers/staging/lustre/lustre/llite/file.c
index 18fb713..391748c 100644
--- a/drivers/staging/lustre/lustre/llite/file.c
+++ b/drivers/staging/lustre/lustre/llite/file.c
@@ -364,7 +364,8 @@ int ll_file_release(struct inode *inode, struct file *file)
 	}
 
 	if (!S_ISDIR(inode->i_mode)) {
-		lov_read_and_clear_async_rc(lli->lli_clob);
+		if (lli->lli_clob)
+			lov_read_and_clear_async_rc(lli->lli_clob);
 		lli->lli_async_rc = 0;
 	}
 
@@ -2593,9 +2594,11 @@ static int ll_flush(struct file *file, fl_owner_t id)
 	 */
 	rc = lli->lli_async_rc;
 	lli->lli_async_rc = 0;
-	err = lov_read_and_clear_async_rc(lli->lli_clob);
-	if (rc == 0)
-		rc = err;
+	if (lli->lli_clob) {
+		err = lov_read_and_clear_async_rc(lli->lli_clob);
+		if (!rc)
+			rc = err;
+	}
 
 	/* The application has been told about write failure already.
 	 * Do not report failure again.
@@ -2825,6 +2828,108 @@ ll_file_flock(struct file *file, int cmd, struct file_lock *file_lock)
 	return rc;
 }
 
+static int ll_get_fid_by_name(struct inode *parent, const char *name,
+			      int namelen, struct lu_fid *fid)
+{
+	struct md_op_data *op_data = NULL;
+	struct ptlrpc_request *req;
+	struct mdt_body *body;
+	int rc;
+
+	op_data = ll_prep_md_op_data(NULL, parent, NULL, name, namelen, 0,
+				     LUSTRE_OPC_ANY, NULL);
+	if (IS_ERR(op_data))
+		return PTR_ERR(op_data);
+
+	op_data->op_valid = OBD_MD_FLID;
+	rc = md_getattr_name(ll_i2sbi(parent)->ll_md_exp, op_data, &req);
+	if (rc < 0)
+		goto out_free;
+
+	body = req_capsule_server_get(&req->rq_pill, &RMF_MDT_BODY);
+	if (!body) {
+		rc = -EFAULT;
+		goto out_req;
+	}
+	*fid = body->fid1;
+out_req:
+	ptlrpc_req_finished(req);
+out_free:
+	if (op_data)
+		ll_finish_md_op_data(op_data);
+	return rc;
+}
+
+int ll_migrate(struct inode *parent, struct file *file, int mdtidx,
+	       const char *name, int namelen)
+{
+	struct ptlrpc_request *request = NULL;
+	struct dentry *dchild = NULL;
+	struct md_op_data *op_data;
+	struct qstr qstr;
+	int rc;
+
+	CDEBUG(D_VFSTRACE, "migrate %s under"DFID" to MDT%d\n",
+	       name, PFID(ll_inode2fid(parent)), mdtidx);
+
+	op_data = ll_prep_md_op_data(NULL, parent, NULL, name, namelen,
+				     0, LUSTRE_OPC_ANY, NULL);
+	if (IS_ERR(op_data))
+		return PTR_ERR(op_data);
+
+	/* Get child FID first */
+	qstr.hash = full_name_hash(name, namelen);
+	qstr.name = name;
+	qstr.len = namelen;
+	dchild = d_lookup(file_dentry(file), &qstr);
+	if (dchild && dchild->d_inode) {
+		op_data->op_fid3 = *ll_inode2fid(dchild->d_inode);
+	} else {
+		rc = ll_get_fid_by_name(parent, name, strnlen(name, namelen),
+					&op_data->op_fid3);
+		if (rc)
+			goto out_free;
+	}
+
+	if (!fid_is_sane(&op_data->op_fid3)) {
+		CERROR("%s: migrate %s, but fid "DFID" is insane\n",
+		       ll_get_fsname(parent->i_sb, NULL, 0), name,
+		       PFID(&op_data->op_fid3));
+		goto out_free;
+	}
+
+	rc = ll_get_mdt_idx_by_fid(ll_i2sbi(parent), &op_data->op_fid3);
+	if (rc < 0)
+		goto out_free;
+
+	if (rc == mdtidx) {
+		CDEBUG(D_INFO, "%s:"DFID" is already on MDT%d.\n", name,
+		       PFID(&op_data->op_fid3), mdtidx);
+		rc = 0;
+		goto out_free;
+	}
+
+	op_data->op_mds = mdtidx;
+	op_data->op_cli_flags = CLI_MIGRATE;
+	rc = md_rename(ll_i2sbi(parent)->ll_md_exp, op_data, name,
+		       strnlen(name, namelen), name, strnlen(name, namelen),
+		       &request);
+	if (!rc)
+		ll_update_times(request, parent);
+
+	ptlrpc_req_finished(request);
+
+out_free:
+	if (dchild) {
+		if (dchild->d_inode)
+			ll_delete_inode(dchild->d_inode);
+		dput(dchild);
+	}
+
+	ll_finish_md_op_data(op_data);
+	return rc;
+}
+
 static int
 ll_file_noflock(struct file *file, int cmd, struct file_lock *file_lock)
 {
diff --git a/drivers/staging/lustre/lustre/llite/llite_internal.h b/drivers/staging/lustre/lustre/llite/llite_internal.h
index 82c3a88..69492f0 100644
--- a/drivers/staging/lustre/lustre/llite/llite_internal.h
+++ b/drivers/staging/lustre/lustre/llite/llite_internal.h
@@ -660,6 +660,7 @@ extern const struct inode_operations ll_dir_inode_operations;
 int ll_dir_read(struct inode *inode, __u64 *ppos, struct md_op_data *op_data,
 		struct dir_context *ctx);
 int ll_get_mdt_idx(struct inode *inode);
+int ll_get_mdt_idx_by_fid(struct ll_sb_info *sbi, const struct lu_fid *fid);
 struct page *ll_get_dir_page(struct inode *dir, struct md_op_data *op_data,
 			     __u64 hash, struct ll_dir_chain *chain);
 void ll_release_page(struct inode *inode, struct page *page, bool remove);
@@ -675,6 +676,7 @@ int ll_test_inode_by_fid(struct inode *inode, void *opaque);
 int ll_md_blocking_ast(struct ldlm_lock *, struct ldlm_lock_desc *,
 		       void *data, int flag);
 struct dentry *ll_splice_alias(struct inode *inode, struct dentry *de);
+void ll_update_times(struct ptlrpc_request *request, struct inode *inode);
 
 /* llite/rw.c */
 int ll_writepage(struct page *page, struct writeback_control *wbc);
@@ -717,7 +719,8 @@ void ll_pack_inode2opdata(struct inode *inode, struct md_op_data *op_data,
 			  struct lustre_handle *fh);
 int ll_getattr(struct vfsmount *mnt, struct dentry *de, struct kstat *stat);
 struct posix_acl *ll_get_acl(struct inode *inode, int type);
-
+int ll_migrate(struct inode *parent, struct file *file, int mdtidx,
+	       const char *name, int namelen);
 int ll_inode_permission(struct inode *inode, int mask);
 
 int ll_lov_setstripe_ea_info(struct inode *inode, struct dentry *dentry,
@@ -777,6 +780,15 @@ int ll_obd_statfs(struct inode *inode, void __user *arg);
 int ll_get_max_mdsize(struct ll_sb_info *sbi, int *max_mdsize);
 int ll_get_default_mdsize(struct ll_sb_info *sbi, int *default_mdsize);
 int ll_process_config(struct lustre_cfg *lcfg);
+
+enum {
+	LUSTRE_OPC_MKDIR	= 0,
+	LUSTRE_OPC_SYMLINK	= 1,
+	LUSTRE_OPC_MKNOD	= 2,
+	LUSTRE_OPC_CREATE	= 3,
+	LUSTRE_OPC_ANY		= 5,
+};
+
 struct md_op_data *ll_prep_md_op_data(struct md_op_data *op_data,
 				      struct inode *i1, struct inode *i2,
 				      const char *name, int namelen,
diff --git a/drivers/staging/lustre/lustre/llite/llite_lib.c b/drivers/staging/lustre/lustre/llite/llite_lib.c
index ef8d87a..e320400 100644
--- a/drivers/staging/lustre/lustre/llite/llite_lib.c
+++ b/drivers/staging/lustre/lustre/llite/llite_lib.c
@@ -1114,8 +1114,34 @@ static void ll_update_lsm_md(struct inode *inode, struct lustre_md *md)
 	struct lmv_stripe_md *lsm = md->lmv;
 	int idx;
 
-	LASSERT(lsm);
 	LASSERT(S_ISDIR(inode->i_mode));
+	CDEBUG(D_INODE, "update lsm %p of "DFID"\n", lli->lli_lsm_md,
+	       PFID(ll_inode2fid(inode)));
+
+	/* no striped information from request. */
+	if (!lsm) {
+		if (!lli->lli_lsm_md) {
+			return;
+		} else if (lli->lli_lsm_md->lsm_md_magic == LMV_MAGIC_MIGRATE) {
+			/*
+			 * migration is done, the temporay MIGRATE layout has
+			 * been removed
+			 */
+			CDEBUG(D_INODE, DFID" finish migration.\n",
+			       PFID(ll_inode2fid(inode)));
+			lmv_free_memmd(lli->lli_lsm_md);
+			lli->lli_lsm_md = NULL;
+			return;
+		} else {
+			/*
+			 * The lustre_md from req does not include stripeEA,
+			 * see ll_md_setattr
+			 */
+			return;
+		}
+	}
+
+	/* set the directory layout */
 	if (!lli->lli_lsm_md) {
 		int rc;
 
@@ -1132,6 +1158,8 @@ static void ll_update_lsm_md(struct inode *inode, struct lustre_md *md)
 		 * will not free this lsm
 		 */
 		md->lmv = NULL;
+		CDEBUG(D_INODE, "Set lsm %p magic %x to "DFID"\n", lsm,
+		       lsm->lsm_md_magic, PFID(ll_inode2fid(inode)));
 		return;
 	}
 
@@ -1668,7 +1696,7 @@ void ll_update_inode(struct inode *inode, struct lustre_md *md)
 			lli->lli_maxbytes = MAX_LFS_FILESIZE;
 	}
 
-	if (S_ISDIR(inode->i_mode) && md->lmv)
+	if (S_ISDIR(inode->i_mode))
 		ll_update_lsm_md(inode, md);
 
 #ifdef CONFIG_FS_POSIX_ACL
@@ -2306,7 +2334,6 @@ struct md_op_data *ll_prep_md_op_data(struct md_op_data *op_data,
 	if ((opc == LUSTRE_OPC_CREATE) && name &&
 	    filename_is_volatile(name, namelen, NULL))
 		op_data->op_bias |= MDS_CREATE_VOLATILE;
-	op_data->op_opc = opc;
 	op_data->op_mds = 0;
 	op_data->op_data = data;
 
diff --git a/drivers/staging/lustre/lustre/llite/namei.c b/drivers/staging/lustre/lustre/llite/namei.c
index 1d28714..41591dd 100644
--- a/drivers/staging/lustre/lustre/llite/namei.c
+++ b/drivers/staging/lustre/lustre/llite/namei.c
@@ -757,8 +757,7 @@ static int ll_create_it(struct inode *dir, struct dentry *dentry, int mode,
 	return 0;
 }
 
-static void ll_update_times(struct ptlrpc_request *request,
-			    struct inode *inode)
+void ll_update_times(struct ptlrpc_request *request, struct inode *inode)
 {
 	struct mdt_body *body = req_capsule_server_get(&request->rq_pill,
 						       &RMF_MDT_BODY);
diff --git a/drivers/staging/lustre/lustre/llite/rw.c b/drivers/staging/lustre/lustre/llite/rw.c
index 87393c4..01aee84 100644
--- a/drivers/staging/lustre/lustre/llite/rw.c
+++ b/drivers/staging/lustre/lustre/llite/rw.c
@@ -1015,6 +1015,10 @@ int ll_writepages(struct address_space *mapping, struct writeback_control *wbc)
 		 * is called later on.
 		 */
 		ignore_layout = 1;
+
+	if (!ll_i2info(inode)->lli_clob)
+		return 0;
+
 	result = cl_sync_file_range(inode, start, end, mode, ignore_layout);
 	if (result > 0) {
 		wbc->nr_to_write -= result;
diff --git a/drivers/staging/lustre/lustre/llite/statahead.c b/drivers/staging/lustre/lustre/llite/statahead.c
index 7b23497..0a28599 100644
--- a/drivers/staging/lustre/lustre/llite/statahead.c
+++ b/drivers/staging/lustre/lustre/llite/statahead.c
@@ -1605,6 +1605,7 @@ int do_statahead_enter(struct inode *dir, struct dentry **dentryp,
 					       *dentryp,
 					       PFID(ll_inode2fid(d_inode(*dentryp))),
 					       PFID(ll_inode2fid(inode)));
+					ll_intent_release(&it);
 					ll_sai_unplug(sai, entry);
 					return -ESTALE;
 				} else {
diff --git a/drivers/staging/lustre/lustre/lmv/lmv_intent.c b/drivers/staging/lustre/lustre/lmv/lmv_intent.c
index 5313dfc..2bc1098 100644
--- a/drivers/staging/lustre/lustre/lmv/lmv_intent.c
+++ b/drivers/staging/lustre/lustre/lmv/lmv_intent.c
@@ -43,6 +43,7 @@
 #include "../include/lustre_lib.h"
 #include "../include/lustre_net.h"
 #include "../include/lustre_dlm.h"
+#include "../include/lustre_mdc.h"
 #include "../include/obd_class.h"
 #include "../include/lprocfs_status.h"
 #include "lmv_internal.h"
@@ -332,6 +333,8 @@ static int lmv_intent_open(struct obd_export *exp, struct md_op_data *op_data,
 
 			oinfo = lsm_name_to_stripe_info(lsm, op_data->op_name,
 							op_data->op_namelen);
+			if (IS_ERR(oinfo))
+				return PTR_ERR(oinfo);
 			op_data->op_fid1 = oinfo->lmo_fid;
 		}
 
@@ -408,6 +411,7 @@ static int lmv_intent_lookup(struct obd_export *exp,
 			     ldlm_blocking_callback cb_blocking,
 			     __u64 extra_lock_flags)
 {
+	struct lmv_stripe_md *lsm = op_data->op_mea1;
 	struct obd_device      *obd = exp->exp_obd;
 	struct lmv_obd	 *lmv = &obd->u.lmv;
 	struct lmv_tgt_desc    *tgt = NULL;
@@ -421,17 +425,15 @@ static int lmv_intent_lookup(struct obd_export *exp,
 	if (!fid_is_sane(&op_data->op_fid2))
 		fid_zero(&op_data->op_fid2);
 
-	CDEBUG(D_INODE, "LOOKUP_INTENT with fid1="DFID", fid2="DFID
-	       ", name='%s' -> mds #%d\n", PFID(&op_data->op_fid1),
-	       PFID(&op_data->op_fid2),
+	CDEBUG(D_INODE, "LOOKUP_INTENT with fid1="DFID", fid2="DFID", name='%s' -> mds #%d lsm=%p lsm_magic=%x\n",
+	       PFID(&op_data->op_fid1), PFID(&op_data->op_fid2),
 	       op_data->op_name ? op_data->op_name : "<NULL>",
-	       tgt->ltd_idx);
+	       tgt->ltd_idx, lsm, !lsm ? -1 : lsm->lsm_md_magic);
 
 	op_data->op_bias &= ~MDS_CROSS_REF;
 
 	rc = md_intent_lock(tgt->ltd_exp, op_data, lmm, lmmsize, it,
 			    flags, reqp, cb_blocking, extra_lock_flags);
-
 	if (rc < 0)
 		return rc;
 
@@ -448,6 +450,26 @@ static int lmv_intent_lookup(struct obd_export *exp,
 				return rc;
 		}
 		return rc;
+	} else if (it_disposition(it, DISP_LOOKUP_NEG) && lsm &&
+		   lsm->lsm_md_magic == LMV_MAGIC_MIGRATE) {
+		/*
+		 * For migrating directory, if it can not find the child in
+		 * the source directory(master stripe), try the targeting
+		 * directory(stripe 1)
+		 */
+		tgt = lmv_find_target(lmv, &lsm->lsm_md_oinfo[1].lmo_fid);
+		if (IS_ERR(tgt))
+			return PTR_ERR(tgt);
+
+		ptlrpc_req_finished(*reqp);
+		CDEBUG(D_INODE, "For migrating dir, try target dir "DFID"\n",
+		       PFID(&lsm->lsm_md_oinfo[1].lmo_fid));
+
+		op_data->op_fid1 = lsm->lsm_md_oinfo[1].lmo_fid;
+		it->it_disposition &= ~DISP_ENQ_COMPLETE;
+		rc = md_intent_lock(tgt->ltd_exp, op_data, lmm, lmmsize, it,
+				    flags, reqp, cb_blocking, extra_lock_flags);
+		return rc;
 	}
 
 	/*
diff --git a/drivers/staging/lustre/lustre/lmv/lmv_obd.c b/drivers/staging/lustre/lustre/lmv/lmv_obd.c
index 4995735..e51ea1f 100644
--- a/drivers/staging/lustre/lustre/lmv/lmv_obd.c
+++ b/drivers/staging/lustre/lustre/lmv/lmv_obd.c
@@ -98,6 +98,15 @@ int lmv_name_to_stripe_index(enum lmv_hash_type hashtype,
 	case LMV_HASH_TYPE_FNV_1A_64:
 		idx = lmv_hash_fnv1a(max_mdt_index, name, namelen);
 		break;
+	/*
+	 * LMV_HASH_TYPE_MIGRATION means the file is being migrated,
+	 * and the file should be accessed by client, except for
+	 * lookup(see lmv_intent_lookup), return -EACCES here
+	 */
+	case LMV_HASH_TYPE_MIGRATION:
+		CERROR("%.*s is being migrated: rc = %d\n", namelen,
+		       name, -EACCES);
+		return -EACCES;
 	default:
 		CERROR("Unknown hash type 0x%x\n", hashtype);
 		return -EINVAL;
@@ -1669,6 +1678,9 @@ lmv_locate_target_for_name(struct lmv_obd *lmv, struct lmv_stripe_md *lsm,
 	struct lmv_tgt_desc *tgt;
 
 	oinfo = lsm_name_to_stripe_info(lsm, name, namelen);
+	if (IS_ERR(oinfo))
+		return ERR_CAST(oinfo);
+
 	*fid = oinfo->lmo_fid;
 	*mds = oinfo->lmo_mds;
 	tgt = lmv_get_target(lmv, *mds);
@@ -1685,7 +1697,8 @@ struct lmv_tgt_desc
 	struct lmv_tgt_desc *tgt;
 
 	if (!lsm || lsm->lsm_md_stripe_count <= 1 ||
-	    !op_data->op_namelen) {
+	    !op_data->op_namelen ||
+	    lsm->lsm_md_magic == LMV_MAGIC_MIGRATE) {
 		tgt = lmv_find_target(lmv, fid);
 		if (IS_ERR(tgt))
 			return tgt;
@@ -1931,23 +1944,24 @@ lmv_getattr_name(struct obd_export *exp, struct md_op_data *op_data,
 	 fl == MF_MDC_CANCEL_FID4 ? &op_data->op_fid4 : \
 	 NULL)
 
-static int lmv_early_cancel(struct obd_export *exp, struct md_op_data *op_data,
-			    int op_tgt, enum ldlm_mode mode, int bits,
-			    int flag)
+static int lmv_early_cancel(struct obd_export *exp, struct lmv_tgt_desc *tgt,
+			    struct md_op_data *op_data, int op_tgt,
+			    enum ldlm_mode mode, int bits, int flag)
 {
 	struct lu_fid	  *fid = md_op_data_fid(op_data, flag);
 	struct obd_device      *obd = exp->exp_obd;
 	struct lmv_obd	 *lmv = &obd->u.lmv;
-	struct lmv_tgt_desc    *tgt;
 	ldlm_policy_data_t      policy = { {0} };
 	int		     rc = 0;
 
 	if (!fid_is_sane(fid))
 		return 0;
 
-	tgt = lmv_find_target(lmv, fid);
-	if (IS_ERR(tgt))
-		return PTR_ERR(tgt);
+	if (!tgt) {
+		tgt = lmv_find_target(lmv, fid);
+		if (IS_ERR(tgt))
+			return PTR_ERR(tgt);
+	}
 
 	if (tgt->ltd_idx != op_tgt) {
 		CDEBUG(D_INODE, "EARLY_CANCEL on "DFID"\n", PFID(fid));
@@ -1996,6 +2010,9 @@ static int lmv_link(struct obd_export *exp, struct md_op_data *op_data,
 
 		oinfo = lsm_name_to_stripe_info(lsm, op_data->op_name,
 						op_data->op_namelen);
+		if (IS_ERR(oinfo))
+			return PTR_ERR(oinfo);
+
 		op_data->op_fid2 = oinfo->lmo_fid;
 	}
 
@@ -2007,7 +2024,7 @@ static int lmv_link(struct obd_export *exp, struct md_op_data *op_data,
 	 * Cancel UPDATE lock on child (fid1).
 	 */
 	op_data->op_flags |= MF_MDC_CANCEL_FID2;
-	rc = lmv_early_cancel(exp, op_data, tgt->ltd_idx, LCK_EX,
+	rc = lmv_early_cancel(exp, NULL, op_data, tgt->ltd_idx, LCK_EX,
 			      MDS_INODELOCK_UPDATE, MF_MDC_CANCEL_FID1);
 	if (rc != 0)
 		return rc;
@@ -2042,31 +2059,44 @@ static int lmv_rename(struct obd_export *exp, struct md_op_data *op_data,
 	op_data->op_fsgid = from_kgid(&init_user_ns, current_fsgid());
 	op_data->op_cap = cfs_curproc_cap_pack();
 
-	if (op_data->op_mea1) {
-		struct lmv_stripe_md *lsm = op_data->op_mea1;
-		const struct lmv_oinfo *oinfo;
-
-		oinfo = lsm_name_to_stripe_info(lsm, old, oldlen);
-		op_data->op_fid1 = oinfo->lmo_fid;
-		op_data->op_mds = oinfo->lmo_mds;
-		src_tgt = lmv_get_target(lmv, op_data->op_mds);
-		if (IS_ERR(src_tgt))
-			return PTR_ERR(src_tgt);
+	if (op_data->op_cli_flags & CLI_MIGRATE) {
+		LASSERTF(fid_is_sane(&op_data->op_fid3), "invalid FID "DFID"\n",
+			 PFID(&op_data->op_fid3));
+		rc = lmv_fid_alloc(exp, &op_data->op_fid2, op_data);
+		if (rc)
+			return rc;
+		src_tgt = lmv_locate_mds(lmv, op_data, &op_data->op_fid3);
 	} else {
-		src_tgt = lmv_find_target(lmv, &op_data->op_fid1);
-		if (IS_ERR(src_tgt))
-			return PTR_ERR(src_tgt);
+		if (op_data->op_mea1) {
+			struct lmv_stripe_md *lsm = op_data->op_mea1;
+
+			src_tgt = lmv_locate_target_for_name(lmv, lsm, old,
+							     oldlen,
+							     &op_data->op_fid1,
+							     &op_data->op_mds);
+			if (IS_ERR(src_tgt))
+				return PTR_ERR(src_tgt);
+		} else {
+			src_tgt = lmv_find_target(lmv, &op_data->op_fid1);
+			if (IS_ERR(src_tgt))
+				return PTR_ERR(src_tgt);
 
-		op_data->op_mds = src_tgt->ltd_idx;
-	}
+			op_data->op_mds = src_tgt->ltd_idx;
+		}
 
-	if (op_data->op_mea2) {
-		struct lmv_stripe_md *lsm = op_data->op_mea2;
-		const struct lmv_oinfo *oinfo;
+		if (op_data->op_mea2) {
+			struct lmv_stripe_md *lsm = op_data->op_mea2;
+			const struct lmv_oinfo *oinfo;
 
-		oinfo = lsm_name_to_stripe_info(lsm, new, newlen);
-		op_data->op_fid2 = oinfo->lmo_fid;
+			oinfo = lsm_name_to_stripe_info(lsm, new, newlen);
+			if (IS_ERR(oinfo))
+				return PTR_ERR(oinfo);
+
+			op_data->op_fid2 = oinfo->lmo_fid;
+		}
 	}
+	if (IS_ERR(src_tgt))
+		return PTR_ERR(src_tgt);
 
 	/*
 	 * LOOKUP lock on src child (fid3) should also be cancelled for
@@ -2078,33 +2108,48 @@ static int lmv_rename(struct obd_export *exp, struct md_op_data *op_data,
 	 * Cancel UPDATE locks on tgt parent (fid2), tgt_tgt is its
 	 * own target.
 	 */
-	rc = lmv_early_cancel(exp, op_data, src_tgt->ltd_idx,
+	rc = lmv_early_cancel(exp, NULL, op_data, src_tgt->ltd_idx,
 			      LCK_EX, MDS_INODELOCK_UPDATE,
 			      MF_MDC_CANCEL_FID2);
-
+	if (rc)
+		return rc;
 	/*
-	 * Cancel LOOKUP locks on tgt child (fid4) for parent tgt_tgt.
+	 * Cancel LOOKUP locks on source child (fid3) for parent tgt_tgt.
 	 */
-	if (rc == 0) {
-		rc = lmv_early_cancel(exp, op_data, src_tgt->ltd_idx,
+	if (fid_is_sane(&op_data->op_fid3)) {
+		struct lmv_tgt_desc *tgt;
+
+		tgt = lmv_find_target(lmv, &op_data->op_fid1);
+		if (IS_ERR(tgt))
+			return PTR_ERR(tgt);
+
+		/* Cancel LOOKUP lock on its parent */
+		rc = lmv_early_cancel(exp, tgt, op_data, src_tgt->ltd_idx,
 				      LCK_EX, MDS_INODELOCK_LOOKUP,
-				      MF_MDC_CANCEL_FID4);
+				      MF_MDC_CANCEL_FID3);
+		if (rc)
+			return rc;
+
+		rc = lmv_early_cancel(exp, NULL, op_data, src_tgt->ltd_idx,
+				      LCK_EX, MDS_INODELOCK_FULL,
+				      MF_MDC_CANCEL_FID3);
+		if (rc)
+			return rc;
 	}
 
 	/*
 	 * Cancel all the locks on tgt child (fid4).
 	 */
-	if (rc == 0)
-		rc = lmv_early_cancel(exp, op_data, src_tgt->ltd_idx,
+	if (fid_is_sane(&op_data->op_fid4))
+		rc = lmv_early_cancel(exp, NULL, op_data, src_tgt->ltd_idx,
 				      LCK_EX, MDS_INODELOCK_FULL,
 				      MF_MDC_CANCEL_FID4);
 
 	CDEBUG(D_INODE, DFID":m%d to "DFID"\n", PFID(&op_data->op_fid1),
 	       op_data->op_mds, PFID(&op_data->op_fid2));
 
-	if (rc == 0)
-		rc = md_rename(src_tgt->ltd_exp, op_data, old, oldlen,
-			       new, newlen, request);
+	rc = md_rename(src_tgt->ltd_exp, op_data, old, oldlen,
+		       new, newlen, request);
 	return rc;
 }
 
@@ -2306,6 +2351,7 @@ static int lmv_unlink(struct obd_export *exp, struct md_op_data *op_data,
 {
 	struct obd_device       *obd = exp->exp_obd;
 	struct lmv_obd	  *lmv = &obd->u.lmv;
+	struct lmv_tgt_desc *parent_tgt = NULL;
 	struct lmv_tgt_desc     *tgt = NULL;
 	struct mdt_body		*body;
 	int		     rc;
@@ -2323,12 +2369,16 @@ retry:
 		/* For striped dir, we need to locate the parent as well */
 		if (op_data->op_mea1 &&
 		    op_data->op_mea1->lsm_md_stripe_count > 1) {
+			struct lmv_tgt_desc *tmp;
+
 			LASSERT(op_data->op_name && op_data->op_namelen);
-			lmv_locate_target_for_name(lmv, op_data->op_mea1,
-						   op_data->op_name,
-						   op_data->op_namelen,
-						   &op_data->op_fid1,
-						   &op_data->op_mds);
+			tmp = lmv_locate_target_for_name(lmv, op_data->op_mea1,
+							 op_data->op_name,
+							 op_data->op_namelen,
+							 &op_data->op_fid1,
+							 &op_data->op_mds);
+			if (IS_ERR(tmp))
+				return PTR_ERR(tmp);
 		}
 	} else {
 		tgt = lmv_locate_mds(lmv, op_data, &op_data->op_fid1);
@@ -2352,9 +2402,18 @@ retry:
 	/*
 	 * Cancel FULL locks on child (fid3).
 	 */
-	rc = lmv_early_cancel(exp, op_data, tgt->ltd_idx, LCK_EX,
-			      MDS_INODELOCK_FULL, MF_MDC_CANCEL_FID3);
+	parent_tgt = lmv_find_target(lmv, &op_data->op_fid1);
+	if (IS_ERR(parent_tgt))
+		return PTR_ERR(parent_tgt);
+
+	if (parent_tgt != tgt) {
+		rc = lmv_early_cancel(exp, parent_tgt, op_data, tgt->ltd_idx,
+				      LCK_EX, MDS_INODELOCK_LOOKUP,
+				      MF_MDC_CANCEL_FID3);
+	}
 
+	rc = lmv_early_cancel(exp, NULL, op_data, tgt->ltd_idx, LCK_EX,
+			      MDS_INODELOCK_FULL, MF_MDC_CANCEL_FID3);
 	if (rc != 0)
 		return rc;
 
@@ -2683,13 +2742,25 @@ int lmv_unpack_md(struct obd_export *exp, struct lmv_stripe_md **lsmp,
 	}
 
 	/* Unpack memmd */
-	if (le32_to_cpu(lmm->lmv_magic) != LMV_MAGIC_V1) {
-		CERROR("%s: invalid magic %x.\n", exp->exp_obd->obd_name,
-		       le32_to_cpu(lmm->lmv_magic));
-		return -EINVAL;
+	if (le32_to_cpu(lmm->lmv_magic) != LMV_MAGIC_V1 &&
+	    le32_to_cpu(lmm->lmv_magic) != LMV_MAGIC_MIGRATE &&
+	    le32_to_cpu(lmm->lmv_magic) != LMV_USER_MAGIC) {
+		CERROR("%s: invalid lmv magic %x: rc = %d\n",
+		       exp->exp_obd->obd_name, le32_to_cpu(lmm->lmv_magic),
+		       -EIO);
+		return -EIO;
 	}
 
-	lsm_size = lmv_stripe_md_size(lmv_mds_md_stripe_count_get(lmm));
+	if (le32_to_cpu(lmm->lmv_magic) == LMV_MAGIC_V1 ||
+	    le32_to_cpu(lmm->lmv_magic) == LMV_MAGIC_MIGRATE)
+		lsm_size = lmv_stripe_md_size(lmv_mds_md_stripe_count_get(lmm));
+	else
+		/**
+		 * Unpack default dirstripe(lmv_user_md) to lmv_stripe_md,
+		 * stripecount should be 0 then.
+		 */
+		lsm_size = lmv_stripe_md_size(0);
+
 	if (!lsm) {
 		lsm = libcfs_kvzalloc(lsm_size, GFP_NOFS);
 		if (!lsm)
@@ -2700,6 +2771,7 @@ int lmv_unpack_md(struct obd_export *exp, struct lmv_stripe_md **lsmp,
 
 	switch (le32_to_cpu(lmm->lmv_magic)) {
 	case LMV_MAGIC_V1:
+	case LMV_MAGIC_MIGRATE:
 		rc = lmv_unpack_md_v1(exp, lsm, &lmm->lmv_md_v1);
 		break;
 	default:
diff --git a/drivers/staging/lustre/lustre/mdc/mdc_lib.c b/drivers/staging/lustre/lustre/mdc/mdc_lib.c
index 143bd76..95c4550 100644
--- a/drivers/staging/lustre/lustre/mdc/mdc_lib.c
+++ b/drivers/staging/lustre/lustre/mdc/mdc_lib.c
@@ -390,6 +390,8 @@ void mdc_rename_pack(struct ptlrpc_request *req, struct md_op_data *op_data,
 	rec = req_capsule_client_get(&req->rq_pill, &RMF_REC_REINT);
 
 	/* XXX do something about time, uid, gid */
+	rec->rn_opcode	 = op_data->op_cli_flags & CLI_MIGRATE ?
+				REINT_MIGRATE : REINT_RENAME;
 	rec->rn_opcode   = REINT_RENAME;
 	rec->rn_fsuid    = op_data->op_fsuid;
 	rec->rn_fsgid    = op_data->op_fsgid;
diff --git a/drivers/staging/lustre/lustre/ptlrpc/wiretest.c b/drivers/staging/lustre/lustre/ptlrpc/wiretest.c
index 4c500a9..bc27f8d 100644
--- a/drivers/staging/lustre/lustre/ptlrpc/wiretest.c
+++ b/drivers/staging/lustre/lustre/ptlrpc/wiretest.c
@@ -190,7 +190,9 @@ void lustre_assert_wire_constants(void)
 		 (long long)REINT_SETXATTR);
 	LASSERTF(REINT_RMENTRY == 8, "found %lld\n",
 		 (long long)REINT_RMENTRY);
-	LASSERTF(REINT_MAX == 9, "found %lld\n",
+	LASSERTF(REINT_MIGRATE == 9, "found %lld\n",
+		 (long long)REINT_MIGRATE);
+	LASSERTF(REINT_MAX == 10, "found %lld\n",
 		 (long long)REINT_MAX);
 	LASSERTF(DISP_IT_EXECD == 0x00000001UL, "found 0x%.8xUL\n",
 		(unsigned)DISP_IT_EXECD);
-- 
1.7.1

[PATCH 36/58] staging: lustre: lmv: fix issue found by Klocwork Insight tool

[James Simmons]

From: Dmitry Eremin <dmitry.eremin@intel.com>

'plock.cookie' might be used uninitialized in this function.

sscanf format specification '%d' expects type 'int *' for 'd',
but parameter 3 has a different type '__u32*'

Signed-off-by: Dmitry Eremin <dmitry.eremin@intel.com>
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-4629
Reviewed-on: http://review.whamcloud.com/9390
Reviewed-by: John L. Hammond <john.hammond@intel.com>
Reviewed-by: James Simmons <uja.ornl@gmail.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
Signed-off-by: James Simmons <jsimmons@infradead.org>
---
 drivers/staging/lustre/lustre/lmv/lmv_intent.c |    6 ++++--
 drivers/staging/lustre/lustre/lmv/lmv_obd.c    |    2 +-
 2 files changed, 5 insertions(+), 3 deletions(-)

diff --git a/drivers/staging/lustre/lustre/lmv/lmv_intent.c b/drivers/staging/lustre/lustre/lmv/lmv_intent.c
index 2bc1098..51b7048 100644
--- a/drivers/staging/lustre/lustre/lmv/lmv_intent.c
+++ b/drivers/staging/lustre/lustre/lmv/lmv_intent.c
@@ -137,8 +137,10 @@ static int lmv_intent_remote(struct obd_export *exp, void *lmm,
 		it->it_remote_lock_mode = it->it_lock_mode;
 	}
 
-	it->it_lock_handle = plock.cookie;
-	it->it_lock_mode = pmode;
+	if (pmode) {
+		it->it_lock_handle = plock.cookie;
+		it->it_lock_mode = pmode;
+	}
 
 out_free_op_data:
 	kfree(op_data);
diff --git a/drivers/staging/lustre/lustre/lmv/lmv_obd.c b/drivers/staging/lustre/lustre/lmv/lmv_obd.c
index e51ea1f..9e3d35a 100644
--- a/drivers/staging/lustre/lustre/lmv/lmv_obd.c
+++ b/drivers/staging/lustre/lustre/lmv/lmv_obd.c
@@ -1421,7 +1421,7 @@ static int lmv_process_config(struct obd_device *obd, u32 len, void *buf)
 
 		obd_str2uuid(&obd_uuid,  lustre_cfg_buf(lcfg, 1));
 
-		if (sscanf(lustre_cfg_buf(lcfg, 2), "%d", &index) != 1) {
+		if (sscanf(lustre_cfg_buf(lcfg, 2), "%u", &index) != 1) {
 			rc = -EINVAL;
 			goto out;
 		}
-- 
1.7.1

[PATCH 37/58] staging: lustre: libcfs: Only dump log once per sec. to avoid EEXIST

[James Simmons]

From: Ryan Haasken <haasken@cray.com>

Since the log file name contains the current time in seconds, dumping
the logs more than once per second causes EEXIST errors to be emitted.
Add a static variable to libcfs_debug_dumplog_internal that records
the time of the last Lustre log dump.  If the current time in seconds
is equal to the last time, do not dump logs again.

Note that this is not thread-safe.  However, in the rare case that two
threads try to access last_dump_time simultaneously, the worst thing
that could happen is that one of the threads will get an EEXIST error
when trying to write the log file.  This is no worse than the current
situation, and it is not likely to happen.

Signed-off-by: Ryan Haasken <haasken@cray.com>
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-4129
Reviewed-on: http://review.whamcloud.com/8964
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Reviewed-by: Bob Glossman <bob.glossman@intel.com>
Signed-off-by: James Simmons <jsimmons@infradead.org>
---
 drivers/staging/lustre/lnet/libcfs/debug.c |    9 +++++++--
 1 files changed, 7 insertions(+), 2 deletions(-)

diff --git a/drivers/staging/lustre/lnet/libcfs/debug.c b/drivers/staging/lustre/lnet/libcfs/debug.c
index 42b15a7..23b36b8 100644
--- a/drivers/staging/lustre/lnet/libcfs/debug.c
+++ b/drivers/staging/lustre/lnet/libcfs/debug.c
@@ -328,15 +328,20 @@ libcfs_debug_str2mask(int *mask, const char *str, int is_subsys)
  */
 void libcfs_debug_dumplog_internal(void *arg)
 {
+	static time64_t last_dump_time;
+	time64_t current_time;
 	void *journal_info;
 
 	journal_info = current->journal_info;
 	current->journal_info = NULL;
+	current_time = ktime_get_real_seconds();
 
-	if (strncmp(libcfs_debug_file_path_arr, "NONE", 4) != 0) {
+	if (strncmp(libcfs_debug_file_path_arr, "NONE", 4) &&
+	    current_time > last_dump_time) {
+		last_dump_time = current_time;
 		snprintf(debug_file_name, sizeof(debug_file_name) - 1,
 			 "%s.%lld.%ld", libcfs_debug_file_path_arr,
-			 (s64)ktime_get_real_seconds(), (long_ptr_t)arg);
+			 (s64)current_time, (long_ptr_t)arg);
 		pr_alert("LustreError: dumping log to %s\n", debug_file_name);
 		cfs_tracefile_dump_all_pages(debug_file_name);
 		libcfs_run_debug_log_upcall(debug_file_name);
-- 
1.7.1

[PATCH 38/58] staging: lustre: llite: enable clients to inject error for lfsck

[James Simmons]

From: Fan Yong <fan.yong@intel.com>

This enables the client to inject an error by altering
the parent FID in order to test if the server side file
system checker behaves properly.

Signed-off-by: Fan Yong <fan.yong@intel.com>
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-3951
Reviewed-on: http://review.whamcloud.com/7667
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Reviewed-by: Alex Zhuravlev <alexey.zhuravlev@intel.com>
Signed-off-by: James Simmons <jsimmons@infradead.org>
---
 .../staging/lustre/lustre/include/obd_support.h    |    1 +
 drivers/staging/lustre/lustre/llite/vvp_req.c      |    2 ++
 2 files changed, 3 insertions(+), 0 deletions(-)

diff --git a/drivers/staging/lustre/lustre/include/obd_support.h b/drivers/staging/lustre/lustre/include/obd_support.h
index 845e64a..71bf844 100644
--- a/drivers/staging/lustre/lustre/include/obd_support.h
+++ b/drivers/staging/lustre/lustre/include/obd_support.h
@@ -474,6 +474,7 @@ extern char obd_jobid_var[];
 #define OBD_FAIL_LFSCK_CRASH		0x160a
 #define OBD_FAIL_LFSCK_NO_AUTO		0x160b
 #define OBD_FAIL_LFSCK_NO_DOUBLESCAN	0x160c
+#define OBD_FAIL_LFSCK_INVALID_PFID	0x1619
 
 /* UPDATE */
 #define OBD_FAIL_UPDATE_OBJ_NET			0x1700
diff --git a/drivers/staging/lustre/lustre/llite/vvp_req.c b/drivers/staging/lustre/lustre/llite/vvp_req.c
index 9fe9d6c..0567a15 100644
--- a/drivers/staging/lustre/lustre/llite/vvp_req.c
+++ b/drivers/staging/lustre/lustre/llite/vvp_req.c
@@ -83,6 +83,8 @@ static void vvp_req_attr_set(const struct lu_env *env,
 	}
 	obdo_from_inode(oa, inode, valid_flags & flags);
 	obdo_set_parent_fid(oa, &ll_i2info(inode)->lli_fid);
+	if (OBD_FAIL_CHECK(OBD_FAIL_LFSCK_INVALID_PFID))
+		oa->o_parent_oid++;
 	memcpy(attr->cra_jobid, ll_i2info(inode)->lli_jobid,
 	       JOBSTATS_JOBID_SIZE);
 }
-- 
1.7.1

[PATCH 39/58] staging: lustre: osc: allow to call brw_commit() multiple times

[James Simmons]

From: Jinshan Xiong <jinshan.xiong@intel.com>

Sometimes the rq_commit_cb of BRW RPC can be called twice if that RPC
has already committed at reply time. This will cause inaccuracy of
unstable pages accounting and then assertion.

Signed-off-by: Jinshan Xiong <jinshan.xiong@intel.com>
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-3274
Reviewed-on: http://review.whamcloud.com/8215
Reviewed-by: Prakash Surya <surya1@llnl.gov>
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
Signed-off-by: James Simmons <jsimmons@infradead.org>
---
 drivers/staging/lustre/lustre/osc/osc_cache.c   |   19 ++++---------------
 drivers/staging/lustre/lustre/osc/osc_request.c |    8 ++++----
 2 files changed, 8 insertions(+), 19 deletions(-)

diff --git a/drivers/staging/lustre/lustre/osc/osc_cache.c b/drivers/staging/lustre/lustre/osc/osc_cache.c
index d1a7d6b..e5c1bc1 100644
--- a/drivers/staging/lustre/lustre/osc/osc_cache.c
+++ b/drivers/staging/lustre/lustre/osc/osc_cache.c
@@ -1875,11 +1875,6 @@ void osc_dec_unstable_pages(struct ptlrpc_request *req)
 	atomic_sub(page_count, &obd_unstable_pages);
 	LASSERT(atomic_read(&obd_unstable_pages) >= 0);
 
-	spin_lock(&req->rq_lock);
-	req->rq_committed = 1;
-	req->rq_unstable  = 0;
-	spin_unlock(&req->rq_lock);
-
 	wake_up_all(&cli->cl_cache->ccc_unstable_waitq);
 }
 
@@ -1909,27 +1904,21 @@ void osc_inc_unstable_pages(struct ptlrpc_request *req)
 	LASSERT(atomic_read(&obd_unstable_pages) >= 0);
 	atomic_add(page_count, &obd_unstable_pages);
 
-	spin_lock(&req->rq_lock);
-
 	/*
 	 * If the request has already been committed (i.e. brw_commit
 	 * called via rq_commit_cb), we need to undo the unstable page
 	 * increments we just performed because rq_commit_cb wont be
-	 * called again. Otherwise, just set the commit callback so the
-	 * unstable page accounting is properly updated when the request
-	 * is committed
+	 * called again.
 	 */
-	if (req->rq_committed) {
+	spin_lock(&req->rq_lock);
+	if (unlikely(req->rq_committed)) {
 		/* Drop lock before calling osc_dec_unstable_pages */
 		spin_unlock(&req->rq_lock);
 		osc_dec_unstable_pages(req);
-		spin_lock(&req->rq_lock);
 	} else {
 		req->rq_unstable = 1;
-		req->rq_commit_cb = osc_dec_unstable_pages;
+		spin_unlock(&req->rq_lock);
 	}
-
-	spin_unlock(&req->rq_lock);
 }
 
 /* this must be called holding the loi list lock to give coverage to exit_cache,
diff --git a/drivers/staging/lustre/lustre/osc/osc_request.c b/drivers/staging/lustre/lustre/osc/osc_request.c
index 536b868..a2d948f 100644
--- a/drivers/staging/lustre/lustre/osc/osc_request.c
+++ b/drivers/staging/lustre/lustre/osc/osc_request.c
@@ -1847,21 +1847,21 @@ static int brw_interpret(const struct lu_env *env,
 
 static void brw_commit(struct ptlrpc_request *req)
 {
-	spin_lock(&req->rq_lock);
 	/*
 	 * If osc_inc_unstable_pages (via osc_extent_finish) races with
 	 * this called via the rq_commit_cb, I need to ensure
 	 * osc_dec_unstable_pages is still called. Otherwise unstable
 	 * pages may be leaked.
 	 */
-	if (req->rq_unstable) {
+	spin_lock(&req->rq_lock);
+	if (unlikely(req->rq_unstable)) {
+		req->rq_unstable = 0;
 		spin_unlock(&req->rq_lock);
 		osc_dec_unstable_pages(req);
-		spin_lock(&req->rq_lock);
 	} else {
 		req->rq_committed = 1;
+		spin_unlock(&req->rq_lock);
 	}
-	spin_unlock(&req->rq_lock);
 }
 
 /**
-- 
1.7.1

[PATCH 40/58] staging: lustre: llite: a few fixes for migration.

[James Simmons]

From: wang di <di.wang@intel.com>

1. Clear the client dentry cache before migrating file/directory
   to the remote MDT.

2. Do not return stripe information to client, if it did not get
   the layout lock.

Signed-off-by: wang di <di.wang@intel.com>
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-4682
Reviewed-on: http://review.whamcloud.com/9522
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>
Signed-off-by: James Simmons <jsimmons@infradead.org>
---
 drivers/staging/lustre/lustre/llite/dir.c          |   22 +++---------
 drivers/staging/lustre/lustre/llite/file.c         |   34 +++++++++++---------
 .../staging/lustre/lustre/llite/llite_internal.h   |    2 +
 drivers/staging/lustre/lustre/lov/lov_object.c     |    1 +
 4 files changed, 28 insertions(+), 31 deletions(-)

diff --git a/drivers/staging/lustre/lustre/llite/dir.c b/drivers/staging/lustre/lustre/llite/dir.c
index ef7322e..84bec03 100644
--- a/drivers/staging/lustre/lustre/llite/dir.c
+++ b/drivers/staging/lustre/lustre/llite/dir.c
@@ -1318,11 +1318,9 @@ static long ll_dir_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 		return 0;
 	}
 	case IOC_MDC_LOOKUP: {
-		struct ptlrpc_request *request = NULL;
 		int namelen, len = 0;
 		char *buf = NULL;
 		char *filename;
-		struct md_op_data *op_data;
 
 		rc = obd_ioctl_getdata(&buf, &len, (void __user *)arg);
 		if (rc)
@@ -1338,21 +1336,13 @@ static long ll_dir_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 			goto out_free;
 		}
 
-		op_data = ll_prep_md_op_data(NULL, inode, NULL, filename, namelen,
-					     0, LUSTRE_OPC_ANY, NULL);
-		if (IS_ERR(op_data)) {
-			rc = PTR_ERR(op_data);
-			goto out_free;
-		}
-
-		op_data->op_valid = OBD_MD_FLID;
-		rc = md_getattr_name(sbi->ll_md_exp, op_data, &request);
-		ll_finish_md_op_data(op_data);
+		rc = ll_get_fid_by_name(inode, filename, namelen, NULL);
 		if (rc < 0) {
-			CDEBUG(D_INFO, "md_getattr_name: %d\n", rc);
+			CERROR("%s: lookup %.*s failed: rc = %d\n",
+			       ll_get_fsname(inode->i_sb, NULL, 0), namelen,
+			       filename, rc);
 			goto out_free;
 		}
-		ptlrpc_req_finished(request);
 out_free:
 		obd_ioctl_freedata(buf, len);
 		return rc;
@@ -1981,7 +1971,7 @@ out_quotactl:
 
 		filename = data->ioc_inlbuf1;
 		namelen = data->ioc_inllen1;
-		if (namelen < 1) {
+		if (namelen < 1 || namelen != strlen(filename) + 1) {
 			rc = -EINVAL;
 			goto migrate_free;
 		}
@@ -1992,7 +1982,7 @@ out_quotactl:
 		}
 		mdtidx = *(int *)data->ioc_inlbuf2;
 
-		rc = ll_migrate(inode, file, mdtidx, filename, namelen);
+		rc = ll_migrate(inode, file, mdtidx, filename, namelen - 1);
 migrate_free:
 		obd_ioctl_freedata(buf, len);
 
diff --git a/drivers/staging/lustre/lustre/llite/file.c b/drivers/staging/lustre/lustre/llite/file.c
index 391748c..4e483c0 100644
--- a/drivers/staging/lustre/lustre/llite/file.c
+++ b/drivers/staging/lustre/lustre/llite/file.c
@@ -2828,8 +2828,8 @@ ll_file_flock(struct file *file, int cmd, struct file_lock *file_lock)
 	return rc;
 }
 
-static int ll_get_fid_by_name(struct inode *parent, const char *name,
-			      int namelen, struct lu_fid *fid)
+int ll_get_fid_by_name(struct inode *parent, const char *name,
+		       int namelen, struct lu_fid *fid)
 {
 	struct md_op_data *op_data = NULL;
 	struct ptlrpc_request *req;
@@ -2843,20 +2843,19 @@ static int ll_get_fid_by_name(struct inode *parent, const char *name,
 
 	op_data->op_valid = OBD_MD_FLID;
 	rc = md_getattr_name(ll_i2sbi(parent)->ll_md_exp, op_data, &req);
+	ll_finish_md_op_data(op_data);
 	if (rc < 0)
-		goto out_free;
+		return rc;
 
 	body = req_capsule_server_get(&req->rq_pill, &RMF_MDT_BODY);
 	if (!body) {
 		rc = -EFAULT;
 		goto out_req;
 	}
-	*fid = body->fid1;
+	if (fid)
+		*fid = body->fid1;
 out_req:
 	ptlrpc_req_finished(req);
-out_free:
-	if (op_data)
-		ll_finish_md_op_data(op_data);
 	return rc;
 }
 
@@ -2864,12 +2863,13 @@ int ll_migrate(struct inode *parent, struct file *file, int mdtidx,
 	       const char *name, int namelen)
 {
 	struct ptlrpc_request *request = NULL;
+	struct inode *child_inode = NULL;
 	struct dentry *dchild = NULL;
 	struct md_op_data *op_data;
 	struct qstr qstr;
 	int rc;
 
-	CDEBUG(D_VFSTRACE, "migrate %s under"DFID" to MDT%d\n",
+	CDEBUG(D_VFSTRACE, "migrate %s under "DFID" to MDT%d\n",
 	       name, PFID(ll_inode2fid(parent)), mdtidx);
 
 	op_data = ll_prep_md_op_data(NULL, parent, NULL, name, namelen,
@@ -2884,8 +2884,13 @@ int ll_migrate(struct inode *parent, struct file *file, int mdtidx,
 	dchild = d_lookup(file_dentry(file), &qstr);
 	if (dchild && dchild->d_inode) {
 		op_data->op_fid3 = *ll_inode2fid(dchild->d_inode);
+		if (dchild->d_inode) {
+			child_inode = igrab(dchild->d_inode);
+			ll_invalidate_aliases(child_inode);
+		}
+		dput(dchild);
 	} else {
-		rc = ll_get_fid_by_name(parent, name, strnlen(name, namelen),
+		rc = ll_get_fid_by_name(parent, name, namelen,
 					&op_data->op_fid3);
 		if (rc)
 			goto out_free;
@@ -2895,6 +2900,7 @@ int ll_migrate(struct inode *parent, struct file *file, int mdtidx,
 		CERROR("%s: migrate %s, but fid "DFID" is insane\n",
 		       ll_get_fsname(parent->i_sb, NULL, 0), name,
 		       PFID(&op_data->op_fid3));
+		rc = -EINVAL;
 		goto out_free;
 	}
 
@@ -2912,18 +2918,16 @@ int ll_migrate(struct inode *parent, struct file *file, int mdtidx,
 	op_data->op_mds = mdtidx;
 	op_data->op_cli_flags = CLI_MIGRATE;
 	rc = md_rename(ll_i2sbi(parent)->ll_md_exp, op_data, name,
-		       strnlen(name, namelen), name, strnlen(name, namelen),
-		       &request);
+		       namelen, name, namelen, &request);
 	if (!rc)
 		ll_update_times(request, parent);
 
 	ptlrpc_req_finished(request);
 
 out_free:
-	if (dchild) {
-		if (dchild->d_inode)
-			ll_delete_inode(dchild->d_inode);
-		dput(dchild);
+	if (child_inode) {
+		clear_nlink(child_inode);
+		iput(child_inode);
 	}
 
 	ll_finish_md_op_data(op_data);
diff --git a/drivers/staging/lustre/lustre/llite/llite_internal.h b/drivers/staging/lustre/lustre/llite/llite_internal.h
index 69492f0..120aca3 100644
--- a/drivers/staging/lustre/lustre/llite/llite_internal.h
+++ b/drivers/staging/lustre/lustre/llite/llite_internal.h
@@ -721,6 +721,8 @@ int ll_getattr(struct vfsmount *mnt, struct dentry *de, struct kstat *stat);
 struct posix_acl *ll_get_acl(struct inode *inode, int type);
 int ll_migrate(struct inode *parent, struct file *file, int mdtidx,
 	       const char *name, int namelen);
+int ll_get_fid_by_name(struct inode *parent, const char *name,
+		       int namelen, struct lu_fid *fid);
 int ll_inode_permission(struct inode *inode, int mask);
 
 int ll_lov_setstripe_ea_info(struct inode *inode, struct dentry *dentry,
diff --git a/drivers/staging/lustre/lustre/lov/lov_object.c b/drivers/staging/lustre/lustre/lov/lov_object.c
index f9621b0..2a52d0c 100644
--- a/drivers/staging/lustre/lustre/lov/lov_object.c
+++ b/drivers/staging/lustre/lustre/lov/lov_object.c
@@ -224,6 +224,7 @@ static int lov_init_raid0(const struct lu_env *env,
 
 	LASSERT(!lov->lo_lsm);
 	lov->lo_lsm = lsm_addref(lsm);
+	lov->lo_layout_invalid = true;
 	r0->lo_nr  = lsm->lsm_stripe_count;
 	LASSERT(r0->lo_nr <= lov_targets_nr(dev));
 
-- 
1.7.1

[PATCH 41/58] staging: lustre: mdc: fixup MDS_SWAP_LAYOUTS ELC handling

[James Simmons]

From: John L. Hammond <john.hammond@intel.com>

In mdc_ioc_swap_layouts() cancel *any* unused locks with LAYOUT or
XATTR IBITS set on the two files. (This matches the locks acquired in
mdt_swap_layouts(). Previously only locks that conflicted with a CR
LAYOUT lock were cancelled.)

Signed-off-by: John L. Hammond <john.hammond@intel.com>
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-4320
Reviewed-on: http://review.whamcloud.com/9329
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Reviewed-by: Faccini Bruno <bruno.faccini@intel.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
Signed-off-by: James Simmons <jsimmons@infradead.org>
---
 drivers/staging/lustre/lustre/mdc/mdc_request.c |    6 ++++--
 1 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/staging/lustre/lustre/mdc/mdc_request.c b/drivers/staging/lustre/lustre/mdc/mdc_request.c
index ab78754..d0a2073 100644
--- a/drivers/staging/lustre/lustre/mdc/mdc_request.c
+++ b/drivers/staging/lustre/lustre/mdc/mdc_request.c
@@ -1670,9 +1670,11 @@ static int mdc_ioc_swap_layouts(struct obd_export *exp,
 	 * with the request RPC to avoid extra RPC round trips
 	 */
 	count = mdc_resource_get_unused(exp, &op_data->op_fid1, &cancels,
-					LCK_CR, MDS_INODELOCK_LAYOUT);
+					LCK_CR, MDS_INODELOCK_LAYOUT |
+					MDS_INODELOCK_XATTR);
 	count += mdc_resource_get_unused(exp, &op_data->op_fid2, &cancels,
-					 LCK_CR, MDS_INODELOCK_LAYOUT);
+					 LCK_CR, MDS_INODELOCK_LAYOUT |
+					 MDS_INODELOCK_XATTR);
 
 	req = ptlrpc_request_alloc(class_exp2cliimp(exp),
 				   &RQF_MDS_SWAP_LAYOUTS);
-- 
1.7.1

[PATCH 42/58] staging: lustre: don't need to const __u64 parameters for lustre_idl.h

[James Simmons]

From: John L. Hammond <john.hammond@intel.com>

Remove the const for the __u64 parameters for inline functions
in lustre_idl.h.

Signed-off-by: John L. Hammond <john.hammond@intel.com>
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-2675
Reviewed-on: http://review.whamcloud.com/8641
Reviewed-by: wangdi <di.wang@intel.com>
Reviewed-by: Fan Yong <fan.yong@intel.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
Signed-off-by: James Simmons <jsimmons@infradead.org>
---
 .../lustre/lustre/include/lustre/lustre_idl.h      |   20 ++++++++++----------
 1 files changed, 10 insertions(+), 10 deletions(-)

diff --git a/drivers/staging/lustre/lustre/include/lustre/lustre_idl.h b/drivers/staging/lustre/lustre/include/lustre/lustre_idl.h
index 6853f62..87e79b9 100644
--- a/drivers/staging/lustre/lustre/include/lustre/lustre_idl.h
+++ b/drivers/staging/lustre/lustre/include/lustre/lustre_idl.h
@@ -442,7 +442,7 @@ static inline int fid_seq_is_mdt0(__u64 seq)
 	return (seq == FID_SEQ_OST_MDT0);
 }
 
-static inline int fid_seq_is_mdt(const __u64 seq)
+static inline int fid_seq_is_mdt(__u64 seq)
 {
 	return seq == FID_SEQ_OST_MDT0 || seq >= FID_SEQ_NORMAL;
 };
@@ -468,33 +468,33 @@ static inline int fid_is_llog(const struct lu_fid *fid)
 	return fid_seq_is_llog(fid_seq(fid)) && fid_oid(fid) > 0;
 }
 
-static inline int fid_seq_is_rsvd(const __u64 seq)
+static inline int fid_seq_is_rsvd(__u64 seq)
 {
 	return (seq > FID_SEQ_OST_MDT0 && seq <= FID_SEQ_RSVD);
 };
 
-static inline int fid_seq_is_special(const __u64 seq)
+static inline int fid_seq_is_special(__u64 seq)
 {
 	return seq == FID_SEQ_SPECIAL;
 };
 
-static inline int fid_seq_is_local_file(const __u64 seq)
+static inline int fid_seq_is_local_file(__u64 seq)
 {
 	return seq == FID_SEQ_LOCAL_FILE ||
 	       seq == FID_SEQ_LOCAL_NAME;
 };
 
-static inline int fid_seq_is_root(const __u64 seq)
+static inline int fid_seq_is_root(__u64 seq)
 {
 	return seq == FID_SEQ_ROOT;
 }
 
-static inline int fid_seq_is_dot(const __u64 seq)
+static inline int fid_seq_is_dot(__u64 seq)
 {
 	return seq == FID_SEQ_DOT_LUSTRE;
 }
 
-static inline int fid_seq_is_default(const __u64 seq)
+static inline int fid_seq_is_default(__u64 seq)
 {
 	return seq == FID_SEQ_LOV_DEFAULT;
 }
@@ -516,7 +516,7 @@ static inline void lu_root_fid(struct lu_fid *fid)
  * \param fid the fid to be tested.
  * \return true if the fid is a igif; otherwise false.
  */
-static inline int fid_seq_is_igif(const __u64 seq)
+static inline int fid_seq_is_igif(__u64 seq)
 {
 	return seq >= FID_SEQ_IGIF && seq <= FID_SEQ_IGIF_MAX;
 }
@@ -531,7 +531,7 @@ static inline int fid_is_igif(const struct lu_fid *fid)
  * \param fid the fid to be tested.
  * \return true if the fid is a idif; otherwise false.
  */
-static inline int fid_seq_is_idif(const __u64 seq)
+static inline int fid_seq_is_idif(__u64 seq)
 {
 	return seq >= FID_SEQ_IDIF && seq <= FID_SEQ_IDIF_MAX;
 }
@@ -546,7 +546,7 @@ static inline int fid_is_local_file(const struct lu_fid *fid)
 	return fid_seq_is_local_file(fid_seq(fid));
 }
 
-static inline int fid_seq_is_norm(const __u64 seq)
+static inline int fid_seq_is_norm(__u64 seq)
 {
 	return (seq >= FID_SEQ_NORMAL);
 }
-- 
1.7.1

[PATCH 43/58] staging: lustre: const correct FID/OSTID/... helpers

[James Simmons]

From: John L. Hammond <john.hammond@intel.com>

Add a const qualifier wherever possible to the pointer parameters of
the inline helper functions in lustre_idl.h and lustre_fid.h.

Signed-off-by: John L. Hammond <john.hammond@intel.com>
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-2675
Reviewed-on: http://review.whamcloud.com/8641
Reviewed-by: wangdi <di.wang@intel.com>
Reviewed-by: Fan Yong <fan.yong@intel.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
Signed-off-by: James Simmons <jsimmons@infradead.org>
---
 .../lustre/lustre/include/lustre/lustre_idl.h      |   28 ++++++++++----------
 drivers/staging/lustre/lustre/include/lustre_fid.h |    9 +++---
 2 files changed, 19 insertions(+), 18 deletions(-)

diff --git a/drivers/staging/lustre/lustre/include/lustre/lustre_idl.h b/drivers/staging/lustre/lustre/include/lustre/lustre_idl.h
index 87e79b9..c932e20 100644
--- a/drivers/staging/lustre/lustre/include/lustre/lustre_idl.h
+++ b/drivers/staging/lustre/lustre/include/lustre/lustre_idl.h
@@ -1033,7 +1033,7 @@ static inline int lu_dirent_calc_size(int namelen, __u16 attr)
 	return (size + 7) & ~7;
 }
 
-static inline int lu_dirent_size(struct lu_dirent *ent)
+static inline int lu_dirent_size(const struct lu_dirent *ent)
 {
 	if (le16_to_cpu(ent->lde_reclen) == 0) {
 		return lu_dirent_calc_size(le16_to_cpu(ent->lde_namelen),
@@ -1067,7 +1067,7 @@ struct lustre_handle {
 
 #define DEAD_HANDLE_MAGIC 0xdeadbeefcafebabeULL
 
-static inline int lustre_handle_is_used(struct lustre_handle *lh)
+static inline int lustre_handle_is_used(const struct lustre_handle *lh)
 {
 	return lh->cookie != 0ull;
 }
@@ -1079,7 +1079,7 @@ static inline int lustre_handle_equal(const struct lustre_handle *lh1,
 }
 
 static inline void lustre_handle_copy(struct lustre_handle *tgt,
-				      struct lustre_handle *src)
+				      const struct lustre_handle *src)
 {
 	tgt->cookie = src->cookie;
 }
@@ -1570,25 +1570,25 @@ static inline void lmm_oi_set_id(struct ost_id *oi, __u64 oid)
 	oi->oi.oi_id = oid;
 }
 
-static inline __u64 lmm_oi_id(struct ost_id *oi)
+static inline __u64 lmm_oi_id(const struct ost_id *oi)
 {
 	return oi->oi.oi_id;
 }
 
-static inline __u64 lmm_oi_seq(struct ost_id *oi)
+static inline __u64 lmm_oi_seq(const struct ost_id *oi)
 {
 	return oi->oi.oi_seq;
 }
 
 static inline void lmm_oi_le_to_cpu(struct ost_id *dst_oi,
-				    struct ost_id *src_oi)
+				    const struct ost_id *src_oi)
 {
 	dst_oi->oi.oi_id = le64_to_cpu(src_oi->oi.oi_id);
 	dst_oi->oi.oi_seq = le64_to_cpu(src_oi->oi.oi_seq);
 }
 
 static inline void lmm_oi_cpu_to_le(struct ost_id *dst_oi,
-				    struct ost_id *src_oi)
+				    const struct ost_id *src_oi)
 {
 	dst_oi->oi.oi_id = cpu_to_le64(src_oi->oi.oi_id);
 	dst_oi->oi.oi_seq = cpu_to_le64(src_oi->oi.oi_seq);
@@ -2724,15 +2724,15 @@ struct ldlm_extent {
 
 #define LDLM_GID_ANY ((__u64)-1)
 
-static inline int ldlm_extent_overlap(struct ldlm_extent *ex1,
-				      struct ldlm_extent *ex2)
+static inline int ldlm_extent_overlap(const struct ldlm_extent *ex1,
+				      const struct ldlm_extent *ex2)
 {
 	return (ex1->start <= ex2->end) && (ex2->start <= ex1->end);
 }
 
 /* check if @ex1 contains @ex2 */
-static inline int ldlm_extent_contain(struct ldlm_extent *ex1,
-				      struct ldlm_extent *ex2)
+static inline int ldlm_extent_contain(const struct ldlm_extent *ex1,
+				      const struct ldlm_extent *ex2)
 {
 	return (ex1->start <= ex2->start) && (ex1->end >= ex2->end);
 }
@@ -3092,7 +3092,7 @@ enum agent_req_status {
 	ARS_SUCCEED,
 };
 
-static inline char *agent_req_status2name(enum agent_req_status ars)
+static inline const char *agent_req_status2name(const enum agent_req_status ars)
 {
 	switch (ars) {
 	case ARS_WAITING:
@@ -3268,7 +3268,7 @@ struct obdo {
 #define o_cksum   o_nlink
 #define o_grant_used o_data_version
 
-static inline void lustre_set_wire_obdo(struct obd_connect_data *ocd,
+static inline void lustre_set_wire_obdo(const struct obd_connect_data *ocd,
 					struct obdo *wobdo,
 					const struct obdo *lobdo)
 {
@@ -3287,7 +3287,7 @@ static inline void lustre_set_wire_obdo(struct obd_connect_data *ocd,
 	}
 }
 
-static inline void lustre_get_wire_obdo(struct obd_connect_data *ocd,
+static inline void lustre_get_wire_obdo(const struct obd_connect_data *ocd,
 					struct obdo *lobdo,
 					const struct obdo *wobdo)
 {
diff --git a/drivers/staging/lustre/lustre/include/lustre_fid.h b/drivers/staging/lustre/lustre/include/lustre_fid.h
index 61f3930..a85183b 100644
--- a/drivers/staging/lustre/lustre/include/lustre_fid.h
+++ b/drivers/staging/lustre/lustre/include/lustre_fid.h
@@ -483,7 +483,7 @@ fid_build_pdo_res_name(const struct lu_fid *fid, unsigned int hash,
  *    res will be built from normal FID directly, i.e. res[0] = f_seq,
  *    res[1] = f_oid + f_ver.
  */
-static inline void ostid_build_res_name(struct ost_id *oi,
+static inline void ostid_build_res_name(const struct ost_id *oi,
 					struct ldlm_res_id *name)
 {
 	memset(name, 0, sizeof(*name));
@@ -498,8 +498,8 @@ static inline void ostid_build_res_name(struct ost_id *oi,
 /**
  * Return true if the resource is for the object identified by this id & group.
  */
-static inline int ostid_res_name_eq(struct ost_id *oi,
-				    struct ldlm_res_id *name)
+static inline int ostid_res_name_eq(const struct ost_id *oi,
+				    const struct ldlm_res_id *name)
 {
 	/* Note: it is just a trick here to save some effort, probably the
 	 * correct way would be turn them into the FID and compare
@@ -610,7 +610,8 @@ static inline __u32 fid_flatten32(const struct lu_fid *fid)
 	return ino ? ino : fid_oid(fid);
 }
 
-static inline int lu_fid_diff(struct lu_fid *fid1, struct lu_fid *fid2)
+static inline int lu_fid_diff(const struct lu_fid *fid1,
+			      const struct lu_fid *fid2)
 {
 	LASSERTF(fid_seq(fid1) == fid_seq(fid2), "fid1:"DFID", fid2:"DFID"\n",
 		 PFID(fid1), PFID(fid2));
-- 
1.7.1

[PATCH 44/58] staging: lustre: use bool for several function in lustre_idl.h/lustre_fid.h

[James Simmons]

From: John L. Hammond <john.hammond@intel.com>

Change the return type of several predicate functions from int to bool.

Signed-off-by: John L. Hammond <john.hammond@intel.com>
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-2675
Reviewed-on: http://review.whamcloud.com/8641
Reviewed-by: wangdi <di.wang@intel.com>
Reviewed-by: Fan Yong <fan.yong@intel.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
Signed-off-by: James Simmons <jsimmons@infradead.org>
---
 .../lustre/lustre/include/lustre/lustre_idl.h      |   72 ++++++++++----------
 drivers/staging/lustre/lustre/include/lustre_fid.h |    4 +-
 2 files changed, 38 insertions(+), 38 deletions(-)

diff --git a/drivers/staging/lustre/lustre/include/lustre/lustre_idl.h b/drivers/staging/lustre/lustre/include/lustre/lustre_idl.h
index c932e20..d3a9db9 100644
--- a/drivers/staging/lustre/lustre/include/lustre/lustre_idl.h
+++ b/drivers/staging/lustre/lustre/include/lustre/lustre_idl.h
@@ -196,12 +196,12 @@ static inline unsigned fld_range_type(const struct lu_seq_range *range)
 	return range->lsr_flags & LU_SEQ_RANGE_MASK;
 }
 
-static inline int fld_range_is_ost(const struct lu_seq_range *range)
+static inline bool fld_range_is_ost(const struct lu_seq_range *range)
 {
 	return fld_range_type(range) == LU_SEQ_RANGE_OST;
 }
 
-static inline int fld_range_is_mdt(const struct lu_seq_range *range)
+static inline bool fld_range_is_mdt(const struct lu_seq_range *range)
 {
 	return fld_range_type(range) == LU_SEQ_RANGE_MDT;
 }
@@ -260,23 +260,23 @@ static inline void range_init(struct lu_seq_range *range)
  * check if given seq id \a s is within given range \a r
  */
 
-static inline int range_within(const struct lu_seq_range *range,
-			       __u64 s)
+static inline bool range_within(const struct lu_seq_range *range,
+				__u64 s)
 {
 	return s >= range->lsr_start && s < range->lsr_end;
 }
 
-static inline int range_is_sane(const struct lu_seq_range *range)
+static inline bool range_is_sane(const struct lu_seq_range *range)
 {
 	return (range->lsr_end >= range->lsr_start);
 }
 
-static inline int range_is_zero(const struct lu_seq_range *range)
+static inline bool range_is_zero(const struct lu_seq_range *range)
 {
 	return (range->lsr_start == 0 && range->lsr_end == 0);
 }
 
-static inline int range_is_exhausted(const struct lu_seq_range *range)
+static inline bool range_is_exhausted(const struct lu_seq_range *range)
 
 {
 	return range_space(range) == 0;
@@ -437,69 +437,69 @@ enum dot_lustre_oid {
 	FID_OID_DOT_LUSTRE_OBF = 2UL,
 };
 
-static inline int fid_seq_is_mdt0(__u64 seq)
+static inline bool fid_seq_is_mdt0(__u64 seq)
 {
 	return (seq == FID_SEQ_OST_MDT0);
 }
 
-static inline int fid_seq_is_mdt(__u64 seq)
+static inline bool fid_seq_is_mdt(__u64 seq)
 {
 	return seq == FID_SEQ_OST_MDT0 || seq >= FID_SEQ_NORMAL;
 };
 
-static inline int fid_seq_is_echo(__u64 seq)
+static inline bool fid_seq_is_echo(__u64 seq)
 {
 	return (seq == FID_SEQ_ECHO);
 }
 
-static inline int fid_is_echo(const struct lu_fid *fid)
+static inline bool fid_is_echo(const struct lu_fid *fid)
 {
 	return fid_seq_is_echo(fid_seq(fid));
 }
 
-static inline int fid_seq_is_llog(__u64 seq)
+static inline bool fid_seq_is_llog(__u64 seq)
 {
 	return (seq == FID_SEQ_LLOG);
 }
 
-static inline int fid_is_llog(const struct lu_fid *fid)
+static inline bool fid_is_llog(const struct lu_fid *fid)
 {
 	/* file with OID == 0 is not llog but contains last oid */
 	return fid_seq_is_llog(fid_seq(fid)) && fid_oid(fid) > 0;
 }
 
-static inline int fid_seq_is_rsvd(__u64 seq)
+static inline bool fid_seq_is_rsvd(__u64 seq)
 {
 	return (seq > FID_SEQ_OST_MDT0 && seq <= FID_SEQ_RSVD);
 };
 
-static inline int fid_seq_is_special(__u64 seq)
+static inline bool fid_seq_is_special(__u64 seq)
 {
 	return seq == FID_SEQ_SPECIAL;
 };
 
-static inline int fid_seq_is_local_file(__u64 seq)
+static inline bool fid_seq_is_local_file(__u64 seq)
 {
 	return seq == FID_SEQ_LOCAL_FILE ||
 	       seq == FID_SEQ_LOCAL_NAME;
 };
 
-static inline int fid_seq_is_root(__u64 seq)
+static inline bool fid_seq_is_root(__u64 seq)
 {
 	return seq == FID_SEQ_ROOT;
 }
 
-static inline int fid_seq_is_dot(__u64 seq)
+static inline bool fid_seq_is_dot(__u64 seq)
 {
 	return seq == FID_SEQ_DOT_LUSTRE;
 }
 
-static inline int fid_seq_is_default(__u64 seq)
+static inline bool fid_seq_is_default(__u64 seq)
 {
 	return seq == FID_SEQ_LOV_DEFAULT;
 }
 
-static inline int fid_is_mdt0(const struct lu_fid *fid)
+static inline bool fid_is_mdt0(const struct lu_fid *fid)
 {
 	return fid_seq_is_mdt0(fid_seq(fid));
 }
@@ -516,12 +516,12 @@ static inline void lu_root_fid(struct lu_fid *fid)
  * \param fid the fid to be tested.
  * \return true if the fid is a igif; otherwise false.
  */
-static inline int fid_seq_is_igif(__u64 seq)
+static inline bool fid_seq_is_igif(__u64 seq)
 {
 	return seq >= FID_SEQ_IGIF && seq <= FID_SEQ_IGIF_MAX;
 }
 
-static inline int fid_is_igif(const struct lu_fid *fid)
+static inline bool fid_is_igif(const struct lu_fid *fid)
 {
 	return fid_seq_is_igif(fid_seq(fid));
 }
@@ -531,27 +531,27 @@ static inline int fid_is_igif(const struct lu_fid *fid)
  * \param fid the fid to be tested.
  * \return true if the fid is a idif; otherwise false.
  */
-static inline int fid_seq_is_idif(__u64 seq)
+static inline bool fid_seq_is_idif(__u64 seq)
 {
 	return seq >= FID_SEQ_IDIF && seq <= FID_SEQ_IDIF_MAX;
 }
 
-static inline int fid_is_idif(const struct lu_fid *fid)
+static inline bool fid_is_idif(const struct lu_fid *fid)
 {
 	return fid_seq_is_idif(fid_seq(fid));
 }
 
-static inline int fid_is_local_file(const struct lu_fid *fid)
+static inline bool fid_is_local_file(const struct lu_fid *fid)
 {
 	return fid_seq_is_local_file(fid_seq(fid));
 }
 
-static inline int fid_seq_is_norm(__u64 seq)
+static inline bool fid_seq_is_norm(__u64 seq)
 {
 	return (seq >= FID_SEQ_NORMAL);
 }
 
-static inline int fid_is_norm(const struct lu_fid *fid)
+static inline bool fid_is_norm(const struct lu_fid *fid)
 {
 	return fid_seq_is_norm(fid_seq(fid));
 }
@@ -769,7 +769,7 @@ static inline int fid_to_ostid(const struct lu_fid *fid, struct ost_id *ostid)
 }
 
 /* Check whether the fid is for LAST_ID */
-static inline int fid_is_last_id(const struct lu_fid *fid)
+static inline bool fid_is_last_id(const struct lu_fid *fid)
 {
 	return (fid_oid(fid) == 0);
 }
@@ -838,7 +838,7 @@ static inline void fid_be_to_cpu(struct lu_fid *dst, const struct lu_fid *src)
 	dst->f_ver = be32_to_cpu(fid_ver(src));
 }
 
-static inline int fid_is_sane(const struct lu_fid *fid)
+static inline bool fid_is_sane(const struct lu_fid *fid)
 {
 	return fid &&
 	       ((fid_seq(fid) >= FID_SEQ_START && fid_ver(fid) == 0) ||
@@ -846,7 +846,7 @@ static inline int fid_is_sane(const struct lu_fid *fid)
 		fid_seq_is_rsvd(fid_seq(fid)));
 }
 
-static inline int fid_is_zero(const struct lu_fid *fid)
+static inline bool fid_is_zero(const struct lu_fid *fid)
 {
 	return fid_seq(fid) == 0 && fid_oid(fid) == 0;
 }
@@ -854,7 +854,7 @@ static inline int fid_is_zero(const struct lu_fid *fid)
 void lustre_swab_lu_fid(struct lu_fid *fid);
 void lustre_swab_lu_seq_range(struct lu_seq_range *range);
 
-static inline int lu_fid_eq(const struct lu_fid *f0, const struct lu_fid *f1)
+static inline bool lu_fid_eq(const struct lu_fid *f0, const struct lu_fid *f1)
 {
 	return memcmp(f0, f1, sizeof(*f0)) == 0;
 }
@@ -1067,13 +1067,13 @@ struct lustre_handle {
 
 #define DEAD_HANDLE_MAGIC 0xdeadbeefcafebabeULL
 
-static inline int lustre_handle_is_used(const struct lustre_handle *lh)
+static inline bool lustre_handle_is_used(const struct lustre_handle *lh)
 {
 	return lh->cookie != 0ull;
 }
 
-static inline int lustre_handle_equal(const struct lustre_handle *lh1,
-				      const struct lustre_handle *lh2)
+static inline bool lustre_handle_equal(const struct lustre_handle *lh1,
+				       const struct lustre_handle *lh2)
 {
 	return lh1->cookie == lh2->cookie;
 }
@@ -2684,8 +2684,8 @@ struct ldlm_res_id {
 #define PLDLMRES(res)	(res)->lr_name.name[0], (res)->lr_name.name[1], \
 			(res)->lr_name.name[2], (res)->lr_name.name[3]
 
-static inline int ldlm_res_eq(const struct ldlm_res_id *res0,
-			      const struct ldlm_res_id *res1)
+static inline bool ldlm_res_eq(const struct ldlm_res_id *res0,
+			       const struct ldlm_res_id *res1)
 {
 	return !memcmp(res0, res1, sizeof(*res0));
 }
diff --git a/drivers/staging/lustre/lustre/include/lustre_fid.h b/drivers/staging/lustre/lustre/include/lustre_fid.h
index a85183b..6f7dc15 100644
--- a/drivers/staging/lustre/lustre/include/lustre_fid.h
+++ b/drivers/staging/lustre/lustre/include/lustre_fid.h
@@ -406,8 +406,8 @@ fid_build_reg_res_name(const struct lu_fid *fid, struct ldlm_res_id *res)
 /*
  * Return true if resource is for object identified by FID.
  */
-static inline int fid_res_name_eq(const struct lu_fid *fid,
-				  const struct ldlm_res_id *res)
+static inline bool fid_res_name_eq(const struct lu_fid *fid,
+				   const struct ldlm_res_id *res)
 {
 	return res->name[LUSTRE_RES_ID_SEQ_OFF] == fid_seq(fid) &&
 	       res->name[LUSTRE_RES_ID_VER_OID_OFF] == fid_ver_oid(fid);
-- 
1.7.1

[PATCH 45/58] staging: lustre: simplify inline functions in lustre_fid.h

[James Simmons]

From: John L. Hammond <john.hammond@intel.com>

Several inline functions return a structure that was passed in.
Their is no need for this so just make these function void.

Signed-off-by: John L. Hammond <john.hammond@intel.com>
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-2675
Reviewed-on: http://review.whamcloud.com/8641
Reviewed-by: wangdi <di.wang@intel.com>
Reviewed-by: Fan Yong <fan.yong@intel.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
Signed-off-by: James Simmons <jsimmons@infradead.org>
---
 drivers/staging/lustre/lustre/include/lustre_fid.h |   16 ++++------------
 1 files changed, 4 insertions(+), 12 deletions(-)

diff --git a/drivers/staging/lustre/lustre/include/lustre_fid.h b/drivers/staging/lustre/lustre/include/lustre_fid.h
index 6f7dc15..f1d5bbd 100644
--- a/drivers/staging/lustre/lustre/include/lustre_fid.h
+++ b/drivers/staging/lustre/lustre/include/lustre_fid.h
@@ -393,14 +393,12 @@ struct ldlm_namespace;
  * but was moved into name[1] along with the OID to avoid consuming the
  * renaming name[2,3] fields that need to be used for the quota identifier.
  */
-static inline struct ldlm_res_id *
+static inline void
 fid_build_reg_res_name(const struct lu_fid *fid, struct ldlm_res_id *res)
 {
 	memset(res, 0, sizeof(*res));
 	res->name[LUSTRE_RES_ID_SEQ_OFF] = fid_seq(fid);
 	res->name[LUSTRE_RES_ID_VER_OID_OFF] = fid_ver_oid(fid);
-
-	return res;
 }
 
 /*
@@ -416,29 +414,25 @@ static inline bool fid_res_name_eq(const struct lu_fid *fid,
 /*
  * Extract FID from LDLM resource. Reverse of fid_build_reg_res_name().
  */
-static inline struct lu_fid *
+static inline void
 fid_extract_from_res_name(struct lu_fid *fid, const struct ldlm_res_id *res)
 {
 	fid->f_seq = res->name[LUSTRE_RES_ID_SEQ_OFF];
 	fid->f_oid = (__u32)(res->name[LUSTRE_RES_ID_VER_OID_OFF]);
 	fid->f_ver = (__u32)(res->name[LUSTRE_RES_ID_VER_OID_OFF] >> 32);
 	LASSERT(fid_res_name_eq(fid, res));
-
-	return fid;
 }
 
 /*
  * Build (DLM) resource identifier from global quota FID and quota ID.
  */
-static inline struct ldlm_res_id *
+static inline void
 fid_build_quota_res_name(const struct lu_fid *glb_fid, union lquota_id *qid,
 			 struct ldlm_res_id *res)
 {
 	fid_build_reg_res_name(glb_fid, res);
 	res->name[LUSTRE_RES_ID_QUOTA_SEQ_OFF] = fid_seq(&qid->qid_fid);
 	res->name[LUSTRE_RES_ID_QUOTA_VER_OID_OFF] = fid_ver_oid(&qid->qid_fid);
-
-	return res;
 }
 
 /*
@@ -455,14 +449,12 @@ static inline void fid_extract_from_quota_res(struct lu_fid *glb_fid,
 		(__u32)(res->name[LUSTRE_RES_ID_QUOTA_VER_OID_OFF] >> 32);
 }
 
-static inline struct ldlm_res_id *
+static inline void
 fid_build_pdo_res_name(const struct lu_fid *fid, unsigned int hash,
 		       struct ldlm_res_id *res)
 {
 	fid_build_reg_res_name(fid, res);
 	res->name[LUSTRE_RES_ID_HSH_OFF] = hash;
-
-	return res;
 }
 
 /**
-- 
1.7.1

[PATCH 46/58] staging: lustre: lmv: access lum_stripe_offset as little endian

[James Simmons]

From: John L. Hammond <john.hammond@intel.com>

By the time that a struct lmv_user_md reaches lmv_placement_policy()
it has already been converted to little endian. Therefore use the
appropriate macros around accesses to this this field. This issue was
found by rewriting the definition of struct lmv_user_md to use the
__leXX typedefs and running sparse.

Signed-off-by: John L. Hammond <john.hammond@intel.com>
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-4738
Reviewed-on: http://review.whamcloud.com/9671
Reviewed-by: Dmitry Eremin <dmitry.eremin@intel.com>
Reviewed-by: Swapnil Pimpale <spimpale@ddn.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
Signed-off-by: James Simmons <jsimmons@infradead.org>
---
 drivers/staging/lustre/lustre/lmv/lmv_obd.c |    6 +++---
 1 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/staging/lustre/lustre/lmv/lmv_obd.c b/drivers/staging/lustre/lustre/lmv/lmv_obd.c
index 9e3d35a..5830fc1 100644
--- a/drivers/staging/lustre/lustre/lmv/lmv_obd.c
+++ b/drivers/staging/lustre/lustre/lmv/lmv_obd.c
@@ -1244,15 +1244,15 @@ static int lmv_placement_policy(struct obd_device *obd,
 		struct lmv_user_md *lum;
 
 		lum = op_data->op_data;
-		if (lum->lum_stripe_offset != (__u32)-1) {
-			*mds = lum->lum_stripe_offset;
+		if (le32_to_cpu(lum->lum_stripe_offset) != (__u32)-1) {
+			*mds = le32_to_cpu(lum->lum_stripe_offset);
 		} else {
 			/*
 			 * -1 means default, which will be in the same MDT with
 			 * the stripe
 			 */
 			*mds = op_data->op_mds;
-			lum->lum_stripe_offset = op_data->op_mds;
+			lum->lum_stripe_offset = cpu_to_le32(op_data->op_mds);
 		}
 	} else {
 		/*
-- 
1.7.1

[PATCH 47/58] staging: lustre: lmv: lookup remote migrating object in LMV

[James Simmons]

From: wang di <di.wang@intel.com>

If remote object is being found in a migrating directory,
it should continue to lookup the object in remote MDT,
instead of return.

Signed-off-by: wang di <di.wang@intel.com>
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-4805
Reviewed-on: http://review.whamcloud.com/9806
Reviewed-by: John L. Hammond <john.hammond@intel.com>
Reviewed-by: Nathaniel Clark <nathaniel.l.clark@intel.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
Signed-off-by: James Simmons <jsimmons@infradead.org>
---
 drivers/staging/lustre/lustre/lmv/lmv_intent.c |    1 -
 1 files changed, 0 insertions(+), 1 deletions(-)

diff --git a/drivers/staging/lustre/lustre/lmv/lmv_intent.c b/drivers/staging/lustre/lustre/lmv/lmv_intent.c
index 51b7048..a38d343 100644
--- a/drivers/staging/lustre/lustre/lmv/lmv_intent.c
+++ b/drivers/staging/lustre/lustre/lmv/lmv_intent.c
@@ -471,7 +471,6 @@ static int lmv_intent_lookup(struct obd_export *exp,
 		it->it_disposition &= ~DISP_ENQ_COMPLETE;
 		rc = md_intent_lock(tgt->ltd_exp, op_data, lmm, lmmsize, it,
 				    flags, reqp, cb_blocking, extra_lock_flags);
-		return rc;
 	}
 
 	/*
-- 
1.7.1

[PATCH 48/58] staging: lustre: lmv: Ensure lmv_intent_lookup cleans up reqp

[James Simmons]

From: Nathaniel Clark <nathaniel.l.clark@intel.com>

Ensure there aren't invalid pointers hanging around after
ptlrpc_req_finished is called.

Signed-off-by: Nathaniel Clark <nathaniel.l.clark@intel.com>
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-4826
Reviewed-on: http://review.whamcloud.com/9841
Reviewed-by: John L. Hammond <john.hammond@intel.com>
Reviewed-by: Bob Glossman <bob.glossman@intel.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
Signed-off-by: James Simmons <jsimmons@infradead.org>
---
 drivers/staging/lustre/lustre/lmv/lmv_intent.c |    3 +++
 1 files changed, 3 insertions(+), 0 deletions(-)

diff --git a/drivers/staging/lustre/lustre/lmv/lmv_intent.c b/drivers/staging/lustre/lustre/lmv/lmv_intent.c
index a38d343..d7e165f 100644
--- a/drivers/staging/lustre/lustre/lmv/lmv_intent.c
+++ b/drivers/staging/lustre/lustre/lmv/lmv_intent.c
@@ -464,6 +464,9 @@ static int lmv_intent_lookup(struct obd_export *exp,
 			return PTR_ERR(tgt);
 
 		ptlrpc_req_finished(*reqp);
+		it->it_request = NULL;
+		*reqp = NULL;
+
 		CDEBUG(D_INODE, "For migrating dir, try target dir "DFID"\n",
 		       PFID(&lsm->lsm_md_oinfo[1].lmo_fid));
 
-- 
1.7.1

[PATCH 49/58] staging: lustre: llite: avoid a deadlock in page write

[James Simmons]

From: Jinshan Xiong <jinshan.xiong@intel.com>

For a partial page write, it will have to issue a READ RPC firstly
to get a full uptodate page. If another page is already locked by
this thread it can easily cause deadlock.

Signed-off-by: Jinshan Xiong <jinshan.xiong@intel.com>
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-4873
Reviewed-on: http://review.whamcloud.com/9928
Reviewed-by: Bobi Jam <bobijam@gmail.com>
Reviewed-by: Niu Yawei <yawei.niu@intel.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
Signed-off-by: James Simmons <jsimmons@infradead.org>
---
 drivers/staging/lustre/lustre/llite/rw26.c |    5 +++--
 1 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/staging/lustre/lustre/llite/rw26.c b/drivers/staging/lustre/lustre/llite/rw26.c
index d98c7ac..c14a1b6 100644
--- a/drivers/staging/lustre/lustre/llite/rw26.c
+++ b/drivers/staging/lustre/lustre/llite/rw26.c
@@ -506,8 +506,9 @@ static int ll_write_begin(struct file *file, struct address_space *mapping,
 	env = lcc->lcc_env;
 	io  = lcc->lcc_io;
 
-	/* To avoid deadlock, try to lock page first. */
-	vmpage = grab_cache_page_nowait(mapping, index);
+	if (likely(to == PAGE_SIZE)) /* LU-4873 */
+		/* To avoid deadlock, try to lock page first. */
+		vmpage = grab_cache_page_nowait(mapping, index);
 	if (unlikely(!vmpage || PageDirty(vmpage) || PageWriteback(vmpage))) {
 		struct vvp_io *vio = vvp_env_io(env);
 		struct cl_page_list *plist = &vio->u.write.vui_queue;
-- 
1.7.1

[PATCH 50/58] staging: lustre: lov: handle the case of stripe size is not power 2

[James Simmons]

From: Jinshan Xiong <jinshan.xiong@intel.com>

Calculate the end of current stripe correctly when the stripe size
is not power 2.

Signed-off-by: Jinshan Xiong <jinshan.xiong@intel.com>
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-4860
Reviewed-on: http://review.whamcloud.com/9882
Reviewed-by: Bobi Jam <bobijam@gmail.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
Signed-off-by: James Simmons <jsimmons@infradead.org>
---
 drivers/staging/lustre/lustre/lov/lov_page.c |   11 +++++++++--
 1 files changed, 9 insertions(+), 2 deletions(-)

diff --git a/drivers/staging/lustre/lustre/lov/lov_page.c b/drivers/staging/lustre/lustre/lov/lov_page.c
index c17026f..45b5ae9 100644
--- a/drivers/staging/lustre/lustre/lov/lov_page.c
+++ b/drivers/staging/lustre/lustre/lov/lov_page.c
@@ -65,7 +65,9 @@ static int lov_raid0_page_is_under_lock(const struct lu_env *env,
 	pgoff_t index = *max_index;
 	unsigned int pps; /* pages per stripe */
 
-	CDEBUG(D_READA, "*max_index = %lu, nr = %d\n", index, r0->lo_nr);
+	CDEBUG(D_READA, DFID "*max_index = %lu, nr = %d\n",
+	       PFID(lu_object_fid(lov2lu(loo))), index, r0->lo_nr);
+
 	if (index == 0) /* the page is not covered by any lock */
 		return 0;
 
@@ -80,7 +82,12 @@ static int lov_raid0_page_is_under_lock(const struct lu_env *env,
 
 	/* calculate the end of current stripe */
 	pps = loo->lo_lsm->lsm_stripe_size >> PAGE_SHIFT;
-	index = ((slice->cpl_index + pps) & ~(pps - 1)) - 1;
+	index = slice->cpl_index + pps - slice->cpl_index % pps - 1;
+
+	CDEBUG(D_READA, DFID "*max_index = %lu, index = %lu, pps = %u, stripe_size = %u, stripe no = %u, page index = %lu\n",
+	       PFID(lu_object_fid(lov2lu(loo))), *max_index, index, pps,
+	       loo->lo_lsm->lsm_stripe_size, lov_page_stripe(slice->cpl_page),
+	       slice->cpl_index);
 
 	/* never exceed the end of the stripe */
 	*max_index = min_t(pgoff_t, *max_index, index);
-- 
1.7.1

[PATCH 51/58] staging: lustre: lmv: cleanup req in lmv_getattr_name()

[James Simmons]

From: John L. Hammond <john.hammond@intel.com>

In lmv_getattr_name() don't return a freed request in the error path.

Signed-off-by: John L. Hammond <john.hammond@intel.com>
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-4826
Reviewed-on: http://review.whamcloud.com/9863
Reviewed-by: Nathaniel Clark <nathaniel.l.clark@intel.com>
Reviewed-by: Bob Glossman <bob.glossman@intel.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
Signed-off-by: James Simmons <jsimmons@infradead.org>
---
 drivers/staging/lustre/lustre/lmv/lmv_obd.c |    1 +
 1 files changed, 1 insertions(+), 0 deletions(-)

diff --git a/drivers/staging/lustre/lustre/lmv/lmv_obd.c b/drivers/staging/lustre/lustre/lmv/lmv_obd.c
index 5830fc1..9982484 100644
--- a/drivers/staging/lustre/lustre/lmv/lmv_obd.c
+++ b/drivers/staging/lustre/lustre/lmv/lmv_obd.c
@@ -1922,6 +1922,7 @@ lmv_getattr_name(struct obd_export *exp, struct md_op_data *op_data,
 		tgt = lmv_find_target(lmv, &rid);
 		if (IS_ERR(tgt)) {
 			ptlrpc_req_finished(*request);
+			*request = NULL;
 			return PTR_ERR(tgt);
 		}
 
-- 
1.7.1

[PATCH 52/58] staging: lustre: lmv: rename request to preq in lmv_getattr_name()

[James Simmons]

From: John L. Hammond <john.hammond@intel.com>

Rename request to preq.

Signed-off-by: John L. Hammond <john.hammond@intel.com>
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-4826
Reviewed-on: http://review.whamcloud.com/9863
Reviewed-by: Nathaniel Clark <nathaniel.l.clark@intel.com>
Reviewed-by: Bob Glossman <bob.glossman@intel.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
Signed-off-by: James Simmons <jsimmons@infradead.org>
---
 drivers/staging/lustre/lustre/lmv/lmv_obd.c |   16 +++++++---------
 1 files changed, 7 insertions(+), 9 deletions(-)

diff --git a/drivers/staging/lustre/lustre/lmv/lmv_obd.c b/drivers/staging/lustre/lustre/lmv/lmv_obd.c
index 9982484..ff0fbd8 100644
--- a/drivers/staging/lustre/lustre/lmv/lmv_obd.c
+++ b/drivers/staging/lustre/lustre/lmv/lmv_obd.c
@@ -1885,7 +1885,7 @@ lmv_enqueue(struct obd_export *exp, struct ldlm_enqueue_info *einfo,
 
 static int
 lmv_getattr_name(struct obd_export *exp, struct md_op_data *op_data,
-		 struct ptlrpc_request **request)
+		 struct ptlrpc_request **preq)
 {
 	struct ptlrpc_request   *req = NULL;
 	struct obd_device       *obd = exp->exp_obd;
@@ -1906,13 +1906,11 @@ lmv_getattr_name(struct obd_export *exp, struct md_op_data *op_data,
 	       op_data->op_namelen, op_data->op_name, PFID(&op_data->op_fid1),
 	       tgt->ltd_idx);
 
-	rc = md_getattr_name(tgt->ltd_exp, op_data, request);
+	rc = md_getattr_name(tgt->ltd_exp, op_data, preq);
 	if (rc != 0)
 		return rc;
 
-	body = req_capsule_server_get(&(*request)->rq_pill,
-				      &RMF_MDT_BODY);
-
+	body = req_capsule_server_get(&(*preq)->rq_pill, &RMF_MDT_BODY);
 	if (body->valid & OBD_MD_MDS) {
 		struct lu_fid rid = body->fid1;
 
@@ -1921,8 +1919,8 @@ lmv_getattr_name(struct obd_export *exp, struct md_op_data *op_data,
 
 		tgt = lmv_find_target(lmv, &rid);
 		if (IS_ERR(tgt)) {
-			ptlrpc_req_finished(*request);
-			*request = NULL;
+			ptlrpc_req_finished(*preq);
+			*preq = NULL;
 			return PTR_ERR(tgt);
 		}
 
@@ -1931,8 +1929,8 @@ lmv_getattr_name(struct obd_export *exp, struct md_op_data *op_data,
 		op_data->op_namelen = 0;
 		op_data->op_name = NULL;
 		rc = md_getattr_name(tgt->ltd_exp, op_data, &req);
-		ptlrpc_req_finished(*request);
-		*request = req;
+		ptlrpc_req_finished(*preq);
+		*preq = req;
 	}
 
 	return rc;
-- 
1.7.1

[PATCH 53/58] staging: lustre: obdclass: unified flow control interfaces

[James Simmons]

From: Fan Yong <fan.yong@intel.com>

Unify the flow control interfaces for MDC RPC and FLD RPC.
We allow to adjust the maximum inflight RPCs count via /sys
interface.

Signed-off-by: Fan Yong <fan.yong@intel.com>
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-4687
Reviewed-on: http://review.whamcloud.com/9562
Reviewed-by: Niu Yawei <yawei.niu@intel.com>
Reviewed-by: Alex Zhuravlev <alexey.zhuravlev@intel.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
Signed-off-by: James Simmons <jsimmons@infradead.org>
---
 drivers/staging/lustre/lustre/fld/fld_request.c    |   55 +--------
 drivers/staging/lustre/lustre/include/lustre_mdc.h |    5 -
 drivers/staging/lustre/lustre/include/obd.h        |   14 +--
 drivers/staging/lustre/lustre/include/obd_class.h  |    5 +
 drivers/staging/lustre/lustre/ldlm/ldlm_lib.c      |    4 +-
 drivers/staging/lustre/lustre/mdc/lproc_mdc.c      |   17 +--
 drivers/staging/lustre/lustre/mdc/mdc_internal.h   |    2 -
 drivers/staging/lustre/lustre/mdc/mdc_lib.c        |   64 ----------
 drivers/staging/lustre/lustre/mdc/mdc_locks.c      |   10 +-
 drivers/staging/lustre/lustre/mdc/mdc_request.c    |    6 +-
 drivers/staging/lustre/lustre/obdclass/genops.c    |  132 ++++++++++++++++++++
 11 files changed, 161 insertions(+), 153 deletions(-)

diff --git a/drivers/staging/lustre/lustre/fld/fld_request.c b/drivers/staging/lustre/lustre/fld/fld_request.c
index e59d626..ed7962e 100644
--- a/drivers/staging/lustre/lustre/fld/fld_request.c
+++ b/drivers/staging/lustre/lustre/fld/fld_request.c
@@ -53,57 +53,6 @@
 #include "../include/lustre_mdc.h"
 #include "fld_internal.h"
 
-/* TODO: these 3 functions are copies of flow-control code from mdc_lib.c
- * It should be common thing. The same about mdc RPC lock
- */
-static int fld_req_avail(struct client_obd *cli, struct mdc_cache_waiter *mcw)
-{
-	int rc;
-
-	spin_lock(&cli->cl_loi_list_lock);
-	rc = list_empty(&mcw->mcw_entry);
-	spin_unlock(&cli->cl_loi_list_lock);
-	return rc;
-};
-
-static void fld_enter_request(struct client_obd *cli)
-{
-	struct mdc_cache_waiter mcw;
-	struct l_wait_info lwi = { 0 };
-
-	spin_lock(&cli->cl_loi_list_lock);
-	if (cli->cl_r_in_flight >= cli->cl_max_rpcs_in_flight) {
-		list_add_tail(&mcw.mcw_entry, &cli->cl_cache_waiters);
-		init_waitqueue_head(&mcw.mcw_waitq);
-		spin_unlock(&cli->cl_loi_list_lock);
-		l_wait_event(mcw.mcw_waitq, fld_req_avail(cli, &mcw), &lwi);
-	} else {
-		cli->cl_r_in_flight++;
-		spin_unlock(&cli->cl_loi_list_lock);
-	}
-}
-
-static void fld_exit_request(struct client_obd *cli)
-{
-	struct list_head *l, *tmp;
-	struct mdc_cache_waiter *mcw;
-
-	spin_lock(&cli->cl_loi_list_lock);
-	cli->cl_r_in_flight--;
-	list_for_each_safe(l, tmp, &cli->cl_cache_waiters) {
-		if (cli->cl_r_in_flight >= cli->cl_max_rpcs_in_flight) {
-			/* No free request slots anymore */
-			break;
-		}
-
-		mcw = list_entry(l, struct mdc_cache_waiter, mcw_entry);
-		list_del_init(&mcw->mcw_entry);
-		cli->cl_r_in_flight++;
-		wake_up(&mcw->mcw_waitq);
-	}
-	spin_unlock(&cli->cl_loi_list_lock);
-}
-
 static int fld_rrb_hash(struct lu_client_fld *fld, u64 seq)
 {
 	LASSERT(fld->lcf_count > 0);
@@ -439,9 +388,9 @@ int fld_client_rpc(struct obd_export *exp,
 	req->rq_reply_portal = MDC_REPLY_PORTAL;
 	ptlrpc_at_set_req_timeout(req);
 
-	fld_enter_request(&exp->exp_obd->u.cli);
+	obd_get_request_slot(&exp->exp_obd->u.cli);
 	rc = ptlrpc_queue_wait(req);
-	fld_exit_request(&exp->exp_obd->u.cli);
+	obd_put_request_slot(&exp->exp_obd->u.cli);
 	if (rc)
 		goto out_req;
 
diff --git a/drivers/staging/lustre/lustre/include/lustre_mdc.h b/drivers/staging/lustre/lustre/include/lustre_mdc.h
index 0a8c639..bf6f87a 100644
--- a/drivers/staging/lustre/lustre/include/lustre_mdc.h
+++ b/drivers/staging/lustre/lustre/include/lustre_mdc.h
@@ -179,11 +179,6 @@ static inline void mdc_update_max_ea_from_body(struct obd_export *exp,
 	}
 }
 
-struct mdc_cache_waiter {
-	struct list_head	      mcw_entry;
-	wait_queue_head_t	     mcw_waitq;
-};
-
 /* mdc/mdc_locks.c */
 int it_open_error(int phase, struct lookup_intent *it);
 
diff --git a/drivers/staging/lustre/lustre/include/obd.h b/drivers/staging/lustre/lustre/include/obd.h
index f5eeb05..cacd472 100644
--- a/drivers/staging/lustre/lustre/include/obd.h
+++ b/drivers/staging/lustre/lustre/include/obd.h
@@ -211,11 +211,12 @@ struct timeout_item {
 	struct list_head	 ti_chain;
 };
 
-#define OSC_MAX_RIF_DEFAULT       8
-#define OSC_MAX_RIF_MAX	 256
-#define OSC_MAX_DIRTY_DEFAULT  (OSC_MAX_RIF_DEFAULT * 4)
-#define OSC_MAX_DIRTY_MB_MAX   2048     /* arbitrary, but < MAX_LONG bytes */
-#define OSC_DEFAULT_RESENDS      10
+#define OBD_MAX_RIF_DEFAULT	8
+#define OBD_MAX_RIF_MAX		512
+#define OSC_MAX_RIF_MAX		256
+#define OSC_MAX_DIRTY_DEFAULT	(OBD_MAX_RIF_DEFAULT * 4)
+#define OSC_MAX_DIRTY_MB_MAX	2048	/* arbitrary, but < MAX_LONG bytes */
+#define OSC_DEFAULT_RESENDS	10
 
 /* possible values for fo_sync_lock_cancel */
 enum {
@@ -225,9 +226,6 @@ enum {
 	NUM_SYNC_ON_CANCEL_STATES
 };
 
-#define MDC_MAX_RIF_DEFAULT       8
-#define MDC_MAX_RIF_MAX	 512
-
 enum obd_cl_sem_lock_class {
 	OBD_CLI_SEM_NORMAL,
 	OBD_CLI_SEM_MGC,
diff --git a/drivers/staging/lustre/lustre/include/obd_class.h b/drivers/staging/lustre/lustre/include/obd_class.h
index 2f111a8..de808ee 100644
--- a/drivers/staging/lustre/lustre/include/obd_class.h
+++ b/drivers/staging/lustre/lustre/include/obd_class.h
@@ -97,6 +97,11 @@ int obd_zombie_impexp_init(void);
 void obd_zombie_impexp_stop(void);
 void obd_zombie_barrier(void);
 
+int obd_get_request_slot(struct client_obd *cli);
+void obd_put_request_slot(struct client_obd *cli);
+__u32 obd_get_max_rpcs_in_flight(struct client_obd *cli);
+int obd_set_max_rpcs_in_flight(struct client_obd *cli, __u32 max);
+
 struct llog_handle;
 struct llog_rec_hdr;
 typedef int (*llog_cb_t)(const struct lu_env *, struct llog_handle *,
diff --git a/drivers/staging/lustre/lustre/ldlm/ldlm_lib.c b/drivers/staging/lustre/lustre/ldlm/ldlm_lib.c
index 7c832aa..ee40006 100644
--- a/drivers/staging/lustre/lustre/ldlm/ldlm_lib.c
+++ b/drivers/staging/lustre/lustre/ldlm/ldlm_lib.c
@@ -360,7 +360,7 @@ int client_obd_setup(struct obd_device *obddev, struct lustre_cfg *lcfg)
 	cli->cl_chunkbits = PAGE_SHIFT;
 
 	if (!strcmp(name, LUSTRE_MDC_NAME)) {
-		cli->cl_max_rpcs_in_flight = MDC_MAX_RIF_DEFAULT;
+		cli->cl_max_rpcs_in_flight = OBD_MAX_RIF_DEFAULT;
 	} else if (totalram_pages >> (20 - PAGE_SHIFT) <= 128 /* MB */) {
 		cli->cl_max_rpcs_in_flight = 2;
 	} else if (totalram_pages >> (20 - PAGE_SHIFT) <= 256 /* MB */) {
@@ -368,7 +368,7 @@ int client_obd_setup(struct obd_device *obddev, struct lustre_cfg *lcfg)
 	} else if (totalram_pages >> (20 - PAGE_SHIFT) <= 512 /* MB */) {
 		cli->cl_max_rpcs_in_flight = 4;
 	} else {
-		cli->cl_max_rpcs_in_flight = OSC_MAX_RIF_DEFAULT;
+		cli->cl_max_rpcs_in_flight = OBD_MAX_RIF_DEFAULT;
 	}
 	rc = ldlm_get_ref();
 	if (rc) {
diff --git a/drivers/staging/lustre/lustre/mdc/lproc_mdc.c b/drivers/staging/lustre/lustre/mdc/lproc_mdc.c
index 98d15fb..fca9450 100644
--- a/drivers/staging/lustre/lustre/mdc/lproc_mdc.c
+++ b/drivers/staging/lustre/lustre/mdc/lproc_mdc.c
@@ -43,11 +43,10 @@ static ssize_t max_rpcs_in_flight_show(struct kobject *kobj,
 	int len;
 	struct obd_device *dev = container_of(kobj, struct obd_device,
 					      obd_kobj);
-	struct client_obd *cli = &dev->u.cli;
+	__u32 max;
 
-	spin_lock(&cli->cl_loi_list_lock);
-	len = sprintf(buf, "%u\n", cli->cl_max_rpcs_in_flight);
-	spin_unlock(&cli->cl_loi_list_lock);
+	max = obd_get_max_rpcs_in_flight(&dev->u.cli);
+	len = sprintf(buf, "%u\n", max);
 
 	return len;
 }
@@ -59,7 +58,6 @@ static ssize_t max_rpcs_in_flight_store(struct kobject *kobj,
 {
 	struct obd_device *dev = container_of(kobj, struct obd_device,
 					      obd_kobj);
-	struct client_obd *cli = &dev->u.cli;
 	int rc;
 	unsigned long val;
 
@@ -67,12 +65,9 @@ static ssize_t max_rpcs_in_flight_store(struct kobject *kobj,
 	if (rc)
 		return rc;
 
-	if (val < 1 || val > MDC_MAX_RIF_MAX)
-		return -ERANGE;
-
-	spin_lock(&cli->cl_loi_list_lock);
-	cli->cl_max_rpcs_in_flight = val;
-	spin_unlock(&cli->cl_loi_list_lock);
+	rc = obd_set_max_rpcs_in_flight(&dev->u.cli, val);
+	if (rc)
+		count = rc;
 
 	return count;
 }
diff --git a/drivers/staging/lustre/lustre/mdc/mdc_internal.h b/drivers/staging/lustre/lustre/mdc/mdc_internal.h
index 58f2841..53b4063 100644
--- a/drivers/staging/lustre/lustre/mdc/mdc_internal.h
+++ b/drivers/staging/lustre/lustre/mdc/mdc_internal.h
@@ -61,8 +61,6 @@ void mdc_link_pack(struct ptlrpc_request *req, struct md_op_data *op_data);
 void mdc_rename_pack(struct ptlrpc_request *req, struct md_op_data *op_data,
 		     const char *old, int oldlen, const char *new, int newlen);
 void mdc_close_pack(struct ptlrpc_request *req, struct md_op_data *op_data);
-int mdc_enter_request(struct client_obd *cli);
-void mdc_exit_request(struct client_obd *cli);
 
 /* mdc/mdc_locks.c */
 int mdc_set_lock_data(struct obd_export *exp,
diff --git a/drivers/staging/lustre/lustre/mdc/mdc_lib.c b/drivers/staging/lustre/lustre/mdc/mdc_lib.c
index 95c4550..b532623 100644
--- a/drivers/staging/lustre/lustre/mdc/mdc_lib.c
+++ b/drivers/staging/lustre/lustre/mdc/mdc_lib.c
@@ -484,67 +484,3 @@ void mdc_close_pack(struct ptlrpc_request *req, struct md_op_data *op_data)
 	mdc_ioepoch_pack(epoch, op_data);
 	mdc_hsm_release_pack(req, op_data);
 }
-
-static int mdc_req_avail(struct client_obd *cli, struct mdc_cache_waiter *mcw)
-{
-	int rc;
-
-	spin_lock(&cli->cl_loi_list_lock);
-	rc = list_empty(&mcw->mcw_entry);
-	spin_unlock(&cli->cl_loi_list_lock);
-	return rc;
-};
-
-/* We record requests in flight in cli->cl_r_in_flight here.
- * There is only one write rpc possible in mdc anyway. If this to change
- * in the future - the code may need to be revisited.
- */
-int mdc_enter_request(struct client_obd *cli)
-{
-	int rc = 0;
-	struct mdc_cache_waiter mcw;
-	struct l_wait_info lwi = LWI_INTR(LWI_ON_SIGNAL_NOOP, NULL);
-
-	spin_lock(&cli->cl_loi_list_lock);
-	if (cli->cl_r_in_flight >= cli->cl_max_rpcs_in_flight) {
-		list_add_tail(&mcw.mcw_entry, &cli->cl_cache_waiters);
-		init_waitqueue_head(&mcw.mcw_waitq);
-		spin_unlock(&cli->cl_loi_list_lock);
-		rc = l_wait_event(mcw.mcw_waitq, mdc_req_avail(cli, &mcw),
-				  &lwi);
-		if (rc) {
-			spin_lock(&cli->cl_loi_list_lock);
-			if (list_empty(&mcw.mcw_entry))
-				cli->cl_r_in_flight--;
-			list_del_init(&mcw.mcw_entry);
-			spin_unlock(&cli->cl_loi_list_lock);
-		}
-	} else {
-		cli->cl_r_in_flight++;
-		spin_unlock(&cli->cl_loi_list_lock);
-	}
-	return rc;
-}
-
-void mdc_exit_request(struct client_obd *cli)
-{
-	struct list_head *l, *tmp;
-	struct mdc_cache_waiter *mcw;
-
-	spin_lock(&cli->cl_loi_list_lock);
-	cli->cl_r_in_flight--;
-	list_for_each_safe(l, tmp, &cli->cl_cache_waiters) {
-		if (cli->cl_r_in_flight >= cli->cl_max_rpcs_in_flight) {
-			/* No free request slots anymore */
-			break;
-		}
-
-		mcw = list_entry(l, struct mdc_cache_waiter, mcw_entry);
-		list_del_init(&mcw->mcw_entry);
-		cli->cl_r_in_flight++;
-		wake_up(&mcw->mcw_waitq);
-	}
-	/* Empty waiting list? Decrease reqs in-flight number */
-
-	spin_unlock(&cli->cl_loi_list_lock);
-}
diff --git a/drivers/staging/lustre/lustre/mdc/mdc_locks.c b/drivers/staging/lustre/lustre/mdc/mdc_locks.c
index 626fce5..d8406d5 100644
--- a/drivers/staging/lustre/lustre/mdc/mdc_locks.c
+++ b/drivers/staging/lustre/lustre/mdc/mdc_locks.c
@@ -809,7 +809,7 @@ resend:
 	 */
 	if (it) {
 		mdc_get_rpc_lock(obddev->u.cli.cl_rpc_lock, it);
-		rc = mdc_enter_request(&obddev->u.cli);
+		rc = obd_get_request_slot(&obddev->u.cli);
 		if (rc != 0) {
 			mdc_put_rpc_lock(obddev->u.cli.cl_rpc_lock, it);
 			mdc_clear_replay_flag(req, 0);
@@ -837,7 +837,7 @@ resend:
 		return rc;
 	}
 
-	mdc_exit_request(&obddev->u.cli);
+	obd_put_request_slot(&obddev->u.cli);
 	mdc_put_rpc_lock(obddev->u.cli.cl_rpc_lock, it);
 
 	if (rc < 0) {
@@ -1179,7 +1179,7 @@ static int mdc_intent_getattr_async_interpret(const struct lu_env *env,
 
 	obddev = class_exp2obd(exp);
 
-	mdc_exit_request(&obddev->u.cli);
+	obd_put_request_slot(&obddev->u.cli);
 	if (OBD_FAIL_CHECK(OBD_FAIL_MDC_GETATTR_ENQUEUE))
 		rc = -ETIMEDOUT;
 
@@ -1239,7 +1239,7 @@ int mdc_intent_getattr_async(struct obd_export *exp,
 	if (IS_ERR(req))
 		return PTR_ERR(req);
 
-	rc = mdc_enter_request(&obddev->u.cli);
+	rc = obd_get_request_slot(&obddev->u.cli);
 	if (rc != 0) {
 		ptlrpc_req_finished(req);
 		return rc;
@@ -1248,7 +1248,7 @@ int mdc_intent_getattr_async(struct obd_export *exp,
 	rc = ldlm_cli_enqueue(exp, &req, einfo, &res_id, &policy, &flags, NULL,
 			      0, LVB_T_NONE, &minfo->mi_lockh, 1);
 	if (rc < 0) {
-		mdc_exit_request(&obddev->u.cli);
+		obd_put_request_slot(&obddev->u.cli);
 		ptlrpc_req_finished(req);
 		return rc;
 	}
diff --git a/drivers/staging/lustre/lustre/mdc/mdc_request.c b/drivers/staging/lustre/lustre/mdc/mdc_request.c
index d0a2073..ce5df23 100644
--- a/drivers/staging/lustre/lustre/mdc/mdc_request.c
+++ b/drivers/staging/lustre/lustre/mdc/mdc_request.c
@@ -58,16 +58,16 @@ static inline int mdc_queue_wait(struct ptlrpc_request *req)
 	struct client_obd *cli = &req->rq_import->imp_obd->u.cli;
 	int rc;
 
-	/* mdc_enter_request() ensures that this client has no more
+	/* obd_get_request_slot() ensures that this client has no more
 	 * than cl_max_rpcs_in_flight RPCs simultaneously inf light
 	 * against an MDT.
 	 */
-	rc = mdc_enter_request(cli);
+	rc = obd_get_request_slot(cli);
 	if (rc != 0)
 		return rc;
 
 	rc = ptlrpc_queue_wait(req);
-	mdc_exit_request(cli);
+	obd_put_request_slot(cli);
 
 	return rc;
 }
diff --git a/drivers/staging/lustre/lustre/obdclass/genops.c b/drivers/staging/lustre/lustre/obdclass/genops.c
index 99c2da6..be25434 100644
--- a/drivers/staging/lustre/lustre/obdclass/genops.c
+++ b/drivers/staging/lustre/lustre/obdclass/genops.c
@@ -1312,3 +1312,135 @@ void obd_zombie_impexp_stop(void)
 	obd_zombie_impexp_notify();
 	wait_for_completion(&obd_zombie_stop);
 }
+
+struct obd_request_slot_waiter {
+	struct list_head	orsw_entry;
+	wait_queue_head_t	orsw_waitq;
+	bool			orsw_signaled;
+};
+
+static bool obd_request_slot_avail(struct client_obd *cli,
+				   struct obd_request_slot_waiter *orsw)
+{
+	bool avail;
+
+	spin_lock(&cli->cl_loi_list_lock);
+	avail = !!list_empty(&orsw->orsw_entry);
+	spin_unlock(&cli->cl_loi_list_lock);
+
+	return avail;
+};
+
+/*
+ * For network flow control, the RPC sponsor needs to acquire a credit
+ * before sending the RPC. The credits count for a connection is defined
+ * by the "cl_max_rpcs_in_flight". If all the credits are occpuied, then
+ * the subsequent RPC sponsors need to wait until others released their
+ * credits, or the administrator increased the "cl_max_rpcs_in_flight".
+ */
+int obd_get_request_slot(struct client_obd *cli)
+{
+	struct obd_request_slot_waiter orsw;
+	struct l_wait_info lwi;
+	int rc;
+
+	spin_lock(&cli->cl_loi_list_lock);
+	if (cli->cl_r_in_flight < cli->cl_max_rpcs_in_flight) {
+		cli->cl_r_in_flight++;
+		spin_unlock(&cli->cl_loi_list_lock);
+		return 0;
+	}
+
+	init_waitqueue_head(&orsw.orsw_waitq);
+	list_add_tail(&orsw.orsw_entry, &cli->cl_loi_read_list);
+	orsw.orsw_signaled = false;
+	spin_unlock(&cli->cl_loi_list_lock);
+
+	lwi = LWI_INTR(LWI_ON_SIGNAL_NOOP, NULL);
+	rc = l_wait_event(orsw.orsw_waitq,
+			  obd_request_slot_avail(cli, &orsw) ||
+			  orsw.orsw_signaled,
+			  &lwi);
+
+	/*
+	 * Here, we must take the lock to avoid the on-stack 'orsw' to be
+	 * freed but other (such as obd_put_request_slot) is using it.
+	 */
+	spin_lock(&cli->cl_loi_list_lock);
+	if (rc) {
+		if (!orsw.orsw_signaled) {
+			if (list_empty(&orsw.orsw_entry))
+				cli->cl_r_in_flight--;
+			else
+				list_del(&orsw.orsw_entry);
+		}
+	}
+
+	if (orsw.orsw_signaled) {
+		LASSERT(list_empty(&orsw.orsw_entry));
+
+		rc = -EINTR;
+	}
+	spin_unlock(&cli->cl_loi_list_lock);
+
+	return rc;
+}
+EXPORT_SYMBOL(obd_get_request_slot);
+
+void obd_put_request_slot(struct client_obd *cli)
+{
+	struct obd_request_slot_waiter *orsw;
+
+	spin_lock(&cli->cl_loi_list_lock);
+	cli->cl_r_in_flight--;
+
+	/* If there is free slot, wakeup the first waiter. */
+	if (!list_empty(&cli->cl_loi_read_list) &&
+	    likely(cli->cl_r_in_flight < cli->cl_max_rpcs_in_flight)) {
+		orsw = list_entry(cli->cl_loi_read_list.next,
+				  struct obd_request_slot_waiter, orsw_entry);
+		list_del_init(&orsw->orsw_entry);
+		cli->cl_r_in_flight++;
+		wake_up(&orsw->orsw_waitq);
+	}
+	spin_unlock(&cli->cl_loi_list_lock);
+}
+EXPORT_SYMBOL(obd_put_request_slot);
+
+__u32 obd_get_max_rpcs_in_flight(struct client_obd *cli)
+{
+	return cli->cl_max_rpcs_in_flight;
+}
+EXPORT_SYMBOL(obd_get_max_rpcs_in_flight);
+
+int obd_set_max_rpcs_in_flight(struct client_obd *cli, __u32 max)
+{
+	struct obd_request_slot_waiter *orsw;
+	__u32 old;
+	int diff;
+	int i;
+
+	if (max > OBD_MAX_RIF_MAX || max < 1)
+		return -ERANGE;
+
+	spin_lock(&cli->cl_loi_list_lock);
+	old = cli->cl_max_rpcs_in_flight;
+	cli->cl_max_rpcs_in_flight = max;
+	diff = max - old;
+
+	/* We increase the max_rpcs_in_flight, then wakeup some waiters. */
+	for (i = 0; i < diff; i++) {
+		if (list_empty(&cli->cl_loi_read_list))
+			break;
+
+		orsw = list_entry(cli->cl_loi_read_list.next,
+				  struct obd_request_slot_waiter, orsw_entry);
+		list_del_init(&orsw->orsw_entry);
+		cli->cl_r_in_flight++;
+		wake_up(&orsw->orsw_waitq);
+	}
+	spin_unlock(&cli->cl_loi_list_lock);
+
+	return 0;
+}
+EXPORT_SYMBOL(obd_set_max_rpcs_in_flight);
-- 
1.7.1

[PATCH 54/58] staging: lustre: reorder LOV_MAGIC_* definition

[James Simmons]

From: Fan Yong <fan.yong@intel.com>

Since all the LOV_MAGIC_* definitions have the same
postfix values break that value out into its own
definition. With this we can check whether the magic's
postfix match the LOV_MAGIC_MAGIC or not: if yes,
then it is quite possible that the clients has
encountered an newer LOV magic. This extra information
can let us handle those cases more gracefully.

Signed-off-by: Fan Yong <fan.yong@intel.com>
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-4941
Reviewed-on: http://review.whamcloud.com/10045
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
Signed-off-by: James Simmons <jsimmons@infradead.org>
---
 .../lustre/lustre/include/lustre/lustre_idl.h      |   20 +++++++++++++++-----
 1 files changed, 15 insertions(+), 5 deletions(-)

diff --git a/drivers/staging/lustre/lustre/include/lustre/lustre_idl.h b/drivers/staging/lustre/lustre/include/lustre/lustre_idl.h
index d3a9db9..3444add 100644
--- a/drivers/staging/lustre/lustre/include/lustre/lustre_idl.h
+++ b/drivers/staging/lustre/lustre/include/lustre/lustre_idl.h
@@ -1478,11 +1478,21 @@ enum obdo_flags {
 	OBD_FL_LOCAL_MASK   = 0xF0000000,
 };
 
-#define LOV_MAGIC_V1      0x0BD10BD0
-#define LOV_MAGIC	 LOV_MAGIC_V1
-#define LOV_MAGIC_JOIN_V1 0x0BD20BD0
-#define LOV_MAGIC_V3      0x0BD30BD0
-#define LOV_MAGIC_MIGRATE 0x0BD40BD0
+/*
+ * All LOV EA magics should have the same postfix, if some new version
+ * Lustre instroduces new LOV EA magic, then when down-grade to an old
+ * Lustre, even though the old version system does not recognizes such
+ * new magic, it still can distinguish the corrupted cases by checking
+ * the magic's postfix.
+ */
+#define LOV_MAGIC_MAGIC 0x0BD0
+#define LOV_MAGIC_MASK  0xFFFF
+
+#define LOV_MAGIC_V1		(0x0BD10000 | LOV_MAGIC_MAGIC)
+#define LOV_MAGIC_JOIN_V1	(0x0BD20000 | LOV_MAGIC_MAGIC)
+#define LOV_MAGIC_V3		(0x0BD30000 | LOV_MAGIC_MAGIC)
+#define LOV_MAGIC_MIGRATE	(0x0BD40000 | LOV_MAGIC_MAGIC)
+#define LOV_MAGIC		LOV_MAGIC_V1
 
 /*
  * magic for fully defined striping
-- 
1.7.1

[PATCH 55/58] staging: lustre: ldlm: flock completion fixes.

[James Simmons]

From: Vitaly Fertman <vitaly_fertman@xyratex.com>

Move checks for FAILED, DESTROYED flags under ldlm spinlock,
destroy flock atomically with the check it is not destroyed yet.
Do not put the granted flock into the resource if this is
UNLOCK, TEST, or DEADLOCK'ed flock.

Later a regression for this patch was reported under LU-7626.
The refcount nonzero (1) after lock cleanup errors was reported.
The reason is that the case LCK_NL was not handled for obdecho.
Patch 17791 resolved this issue which has been combined into
this upstream patch.

Signed-off-by: Vitaly Fertman <vitaly_fertman@xyratex.com>
Signed-off-by: Andriy Skulysh <andriy.skulysh@seagate.com>
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-2177
Reviewed-by: Alexey Lyashkov <alexey_lyashkov@xyratex.com>
Reviewed-by: Andriy Skulysh <andriy_skulysh@xyratex.com>
Reviewed-by: Vitaly Fertman <vitaly_fertman@xyratex.com>
Xyratex-bug-id: MRP-1588
Reviewed-on: http://review.whamcloud.com/10005
Reviewed-by: Bobi Jam <bobijam@gmail.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-7626
Reviewed-by: Mirza Arshad Mirza Hussain <arshad.hussain@seagate.com>
Reviewed-by: Alexey Leonidovich Lyashkov <alexey.lyashkov@seagate.com>
Reviewed-on: http://review.whamcloud.com/17791
Reviewed-by: Niu Yawei <yawei.niu@intel.com>
Reviewed-by: Alex Zhuravlev <alexey.zhuravlev@intel.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
Signed-off-by: James Simmons <jsimmons@infradead.org>
---
 .../lustre/include/linux/libcfs/libcfs_fail.h      |    3 +
 drivers/staging/lustre/lnet/libcfs/fail.c          |    6 +-
 .../lustre/lustre/include/lustre_dlm_flags.h       |   36 ++++---
 .../staging/lustre/lustre/include/obd_support.h    |    4 +
 drivers/staging/lustre/lustre/ldlm/ldlm_flock.c    |   98 ++++++++++++++------
 drivers/staging/lustre/lustre/ldlm/ldlm_lock.c     |   23 ++++-
 drivers/staging/lustre/lustre/ldlm/ldlm_request.c  |   16 ++--
 drivers/staging/lustre/lustre/ldlm/ldlm_resource.c |    8 ++-
 drivers/staging/lustre/lustre/llite/file.c         |   20 +++--
 9 files changed, 148 insertions(+), 66 deletions(-)

diff --git a/drivers/staging/lustre/include/linux/libcfs/libcfs_fail.h b/drivers/staging/lustre/include/linux/libcfs/libcfs_fail.h
index d3f9a60..bdbbe93 100644
--- a/drivers/staging/lustre/include/linux/libcfs/libcfs_fail.h
+++ b/drivers/staging/lustre/include/linux/libcfs/libcfs_fail.h
@@ -143,6 +143,9 @@ static inline int cfs_fail_timeout_set(__u32 id, __u32 value, int ms, int set)
 #define CFS_FAIL_TIMEOUT_ORSET(id, value, secs) \
 	cfs_fail_timeout_set(id, value, secs * 1000, CFS_FAIL_LOC_ORSET)
 
+#define CFS_FAIL_TIMEOUT_RESET(id, value, secs) \
+	cfs_fail_timeout_set(id, value, secs * 1000, CFS_FAIL_LOC_RESET)
+
 #define CFS_FAIL_TIMEOUT_MS_ORSET(id, value, ms) \
 	cfs_fail_timeout_set(id, value, ms, CFS_FAIL_LOC_ORSET)
 
diff --git a/drivers/staging/lustre/lnet/libcfs/fail.c b/drivers/staging/lustre/lnet/libcfs/fail.c
index 9288ee0..e4b1a0a 100644
--- a/drivers/staging/lustre/lnet/libcfs/fail.c
+++ b/drivers/staging/lustre/lnet/libcfs/fail.c
@@ -90,8 +90,10 @@ int __cfs_fail_check_set(__u32 id, __u32 value, int set)
 		}
 	}
 
-	if ((set == CFS_FAIL_LOC_ORSET || set == CFS_FAIL_LOC_RESET) &&
-	    (value & CFS_FAIL_ONCE))
+	/* Take into account the current call for FAIL_ONCE for ORSET only,
+	 * as RESET is a new fail_loc, it does not change the current call
+	 */
+	if ((set == CFS_FAIL_LOC_ORSET) && (value & CFS_FAIL_ONCE))
 		set_bit(CFS_FAIL_ONCE_BIT, &cfs_fail_loc);
 	/* Lost race to set CFS_FAILED_BIT. */
 	if (test_and_set_bit(CFS_FAILED_BIT, &cfs_fail_loc)) {
diff --git a/drivers/staging/lustre/lustre/include/lustre_dlm_flags.h b/drivers/staging/lustre/lustre/include/lustre_dlm_flags.h
index e7e0c21..a0f064d 100644
--- a/drivers/staging/lustre/lustre/include/lustre_dlm_flags.h
+++ b/drivers/staging/lustre/lustre/include/lustre_dlm_flags.h
@@ -28,21 +28,6 @@
 /** l_flags bits marked as "all_flags" bits */
 #define LDLM_FL_ALL_FLAGS_MASK          0x00FFFFFFC08F932FULL
 
-/** l_flags bits marked as "ast" bits */
-#define LDLM_FL_AST_MASK                0x0000000080008000ULL
-
-/** l_flags bits marked as "blocked" bits */
-#define LDLM_FL_BLOCKED_MASK            0x000000000000000EULL
-
-/** l_flags bits marked as "gone" bits */
-#define LDLM_FL_GONE_MASK               0x0006004000000000ULL
-
-/** l_flags bits marked as "inherit" bits */
-#define LDLM_FL_INHERIT_MASK            0x0000000000800000ULL
-
-/** l_flags bits marked as "off_wire" bits */
-#define LDLM_FL_OFF_WIRE_MASK           0x00FFFFFF00000000ULL
-
 /** extent, mode, or resource changed */
 #define LDLM_FL_LOCK_CHANGED            0x0000000000000001ULL /* bit 0 */
 #define ldlm_is_lock_changed(_l)        LDLM_TEST_FLAG((_l), 1ULL <<  0)
@@ -372,6 +357,27 @@
 #define ldlm_set_excl(_l)               LDLM_SET_FLAG((_l), 1ULL << 55)
 #define ldlm_clear_excl(_l)             LDLM_CLEAR_FLAG((_l), 1ULL << 55)
 
+/** l_flags bits marked as "ast" bits */
+#define LDLM_FL_AST_MASK		(LDLM_FL_FLOCK_DEADLOCK		|\
+					 LDLM_FL_AST_DISCARD_DATA)
+
+/** l_flags bits marked as "blocked" bits */
+#define LDLM_FL_BLOCKED_MASK		(LDLM_FL_BLOCK_GRANTED		|\
+					 LDLM_FL_BLOCK_CONV		|\
+					 LDLM_FL_BLOCK_WAIT)
+
+/** l_flags bits marked as "gone" bits */
+#define LDLM_FL_GONE_MASK		(LDLM_FL_DESTROYED		|\
+					 LDLM_FL_FAILED)
+
+/** l_flags bits marked as "inherit" bits */
+/* Flags inherited from wire on enqueue/reply between client/server. */
+/* NO_TIMEOUT flag to force ldlm_lock_match() to wait with no timeout. */
+/* TEST_LOCK flag to not let TEST lock to be granted. */
+#define LDLM_FL_INHERIT_MASK		(LDLM_FL_CANCEL_ON_BLOCK	|\
+					 LDLM_FL_NO_TIMEOUT		|\
+					 LDLM_FL_TEST_LOCK)
+
 /** test for ldlm_lock flag bit set */
 #define LDLM_TEST_FLAG(_l, _b)        (((_l)->l_flags & (_b)) != 0)
 
diff --git a/drivers/staging/lustre/lustre/include/obd_support.h b/drivers/staging/lustre/lustre/include/obd_support.h
index 71bf844..26fdff6 100644
--- a/drivers/staging/lustre/lustre/include/obd_support.h
+++ b/drivers/staging/lustre/lustre/include/obd_support.h
@@ -318,6 +318,10 @@ extern char obd_jobid_var[];
 #define OBD_FAIL_LDLM_AGL_NOLOCK	 0x31b
 #define OBD_FAIL_LDLM_OST_LVB		 0x31c
 #define OBD_FAIL_LDLM_ENQUEUE_HANG	 0x31d
+#define OBD_FAIL_LDLM_CP_CB_WAIT2	 0x320
+#define OBD_FAIL_LDLM_CP_CB_WAIT3	 0x321
+#define OBD_FAIL_LDLM_CP_CB_WAIT4	 0x322
+#define OBD_FAIL_LDLM_CP_CB_WAIT5	 0x323
 
 /* LOCKLESS IO */
 #define OBD_FAIL_LDLM_SET_CONTENTION     0x385
diff --git a/drivers/staging/lustre/lustre/ldlm/ldlm_flock.c b/drivers/staging/lustre/lustre/ldlm/ldlm_flock.c
index d6b61bc..65e8e14 100644
--- a/drivers/staging/lustre/lustre/ldlm/ldlm_flock.c
+++ b/drivers/staging/lustre/lustre/ldlm/ldlm_flock.c
@@ -97,7 +97,7 @@ ldlm_flock_destroy(struct ldlm_lock *lock, enum ldlm_mode mode, __u64 flags)
 	LASSERT(hlist_unhashed(&lock->l_exp_flock_hash));
 
 	list_del_init(&lock->l_res_link);
-	if (flags == LDLM_FL_WAIT_NOREPROC && !ldlm_is_failed(lock)) {
+	if (flags == LDLM_FL_WAIT_NOREPROC) {
 		/* client side - set a flag to prevent sending a CANCEL */
 		lock->l_flags |= LDLM_FL_LOCAL_ONLY | LDLM_FL_CBPENDING;
 
@@ -455,27 +455,21 @@ ldlm_flock_completion_ast(struct ldlm_lock *lock, __u64 flags, void *data)
 	enum ldlm_error		    err;
 	int			     rc = 0;
 
+	OBD_FAIL_TIMEOUT(OBD_FAIL_LDLM_CP_CB_WAIT2, 4);
+	if (OBD_FAIL_PRECHECK(OBD_FAIL_LDLM_CP_CB_WAIT3)) {
+		lock_res_and_lock(lock);
+		lock->l_flags |= LDLM_FL_FAIL_LOC;
+		unlock_res_and_lock(lock);
+		OBD_FAIL_TIMEOUT(OBD_FAIL_LDLM_CP_CB_WAIT3, 4);
+	}
 	CDEBUG(D_DLMTRACE, "flags: 0x%llx data: %p getlk: %p\n",
 	       flags, data, getlk);
 
-	/* Import invalidation. We need to actually release the lock
-	 * references being held, so that it can go away. No point in
-	 * holding the lock even if app still believes it has it, since
-	 * server already dropped it anyway. Only for granted locks too.
-	 */
-	if ((lock->l_flags & (LDLM_FL_FAILED|LDLM_FL_LOCAL_ONLY)) ==
-	    (LDLM_FL_FAILED|LDLM_FL_LOCAL_ONLY)) {
-		if (lock->l_req_mode == lock->l_granted_mode &&
-		    lock->l_granted_mode != LCK_NL && !data)
-			ldlm_lock_decref_internal(lock, lock->l_req_mode);
-
-		/* Need to wake up the waiter if we were evicted */
-		wake_up(&lock->l_waitq);
-		return 0;
-	}
-
 	LASSERT(flags != LDLM_FL_WAIT_NOREPROC);
 
+	if (flags & LDLM_FL_FAILED)
+		goto granted;
+
 	if (!(flags & (LDLM_FL_BLOCK_WAIT | LDLM_FL_BLOCK_GRANTED |
 		       LDLM_FL_BLOCK_CONV))) {
 		if (!data)
@@ -514,12 +508,21 @@ ldlm_flock_completion_ast(struct ldlm_lock *lock, __u64 flags, void *data)
 granted:
 	OBD_FAIL_TIMEOUT(OBD_FAIL_LDLM_CP_CB_WAIT, 10);
 
-	if (ldlm_is_failed(lock)) {
-		LDLM_DEBUG(lock, "client-side enqueue waking up: failed");
-		return -EIO;
+	if (OBD_FAIL_PRECHECK(OBD_FAIL_LDLM_CP_CB_WAIT4)) {
+		lock_res_and_lock(lock);
+		/* DEADLOCK is always set with CBPENDING */
+		lock->l_flags |= LDLM_FL_FLOCK_DEADLOCK | LDLM_FL_CBPENDING;
+		unlock_res_and_lock(lock);
+		OBD_FAIL_TIMEOUT(OBD_FAIL_LDLM_CP_CB_WAIT4, 4);
+	}
+	if (OBD_FAIL_PRECHECK(OBD_FAIL_LDLM_CP_CB_WAIT5)) {
+		lock_res_and_lock(lock);
+		/* DEADLOCK is always set with CBPENDING */
+		lock->l_flags |= LDLM_FL_FAIL_LOC |
+				 LDLM_FL_FLOCK_DEADLOCK | LDLM_FL_CBPENDING;
+		unlock_res_and_lock(lock);
+		OBD_FAIL_TIMEOUT(OBD_FAIL_LDLM_CP_CB_WAIT5, 4);
 	}
-
-	LDLM_DEBUG(lock, "client-side enqueue granted");
 
 	lock_res_and_lock(lock);
 
@@ -530,20 +533,59 @@ granted:
 	if (ldlm_is_destroyed(lock)) {
 		unlock_res_and_lock(lock);
 		LDLM_DEBUG(lock, "client-side enqueue waking up: destroyed");
-		return 0;
+		/*
+		 * An error is still to be returned, to propagate it up to
+		 * ldlm_cli_enqueue_fini() caller.
+		 */
+		return -EIO;
 	}
 
 	/* ldlm_lock_enqueue() has already placed lock on the granted list. */
-	list_del_init(&lock->l_res_link);
+	ldlm_resource_unlink_lock(lock);
+
+	/*
+	 * Import invalidation. We need to actually release the lock
+	 * references being held, so that it can go away. No point in
+	 * holding the lock even if app still believes it has it, since
+	 * server already dropped it anyway. Only for granted locks too.
+	 */
+	/* Do the same for DEADLOCK'ed locks. */
+	if (ldlm_is_failed(lock) || ldlm_is_flock_deadlock(lock)) {
+		int mode;
+
+		if (flags & LDLM_FL_TEST_LOCK)
+			LASSERT(ldlm_is_test_lock(lock));
+
+		if (ldlm_is_test_lock(lock) || ldlm_is_flock_deadlock(lock))
+			mode = getlk->fl_type;
+		else
+			mode = lock->l_granted_mode;
+
+		if (ldlm_is_flock_deadlock(lock)) {
+			LDLM_DEBUG(lock, "client-side enqueue deadlock received");
+			rc = -EDEADLK;
+		}
+		ldlm_flock_destroy(lock, mode, LDLM_FL_WAIT_NOREPROC);
+		unlock_res_and_lock(lock);
+
+		/* Need to wake up the waiter if we were evicted */
+		wake_up(&lock->l_waitq);
+
+		/*
+		 * An error is still to be returned, to propagate it up to
+		 * ldlm_cli_enqueue_fini() caller.
+		 */
+		return rc ? : -EIO;
+	}
+
+	LDLM_DEBUG(lock, "client-side enqueue granted");
 
-	if (ldlm_is_flock_deadlock(lock)) {
-		LDLM_DEBUG(lock, "client-side enqueue deadlock received");
-		rc = -EDEADLK;
-	} else if (flags & LDLM_FL_TEST_LOCK) {
+	if (flags & LDLM_FL_TEST_LOCK) {
 		/* fcntl(F_GETLK) request */
 		/* The old mode was saved in getlk->fl_type so that if the mode
 		 * in the lock changes we can decref the appropriate refcount.
 		 */
+		LASSERT(ldlm_is_test_lock(lock));
 		ldlm_flock_destroy(lock, getlk->fl_type, LDLM_FL_WAIT_NOREPROC);
 		switch (lock->l_granted_mode) {
 		case LCK_PR:
diff --git a/drivers/staging/lustre/lustre/ldlm/ldlm_lock.c b/drivers/staging/lustre/lustre/ldlm/ldlm_lock.c
index a5993f7..1a0fce1 100644
--- a/drivers/staging/lustre/lustre/ldlm/ldlm_lock.c
+++ b/drivers/staging/lustre/lustre/ldlm/ldlm_lock.c
@@ -1028,15 +1028,28 @@ void ldlm_grant_lock(struct ldlm_lock *lock, struct list_head *work_list)
 	check_res_locked(res);
 
 	lock->l_granted_mode = lock->l_req_mode;
+
+	if (work_list && lock->l_completion_ast)
+		ldlm_add_ast_work_item(lock, NULL, work_list);
+
 	if (res->lr_type == LDLM_PLAIN || res->lr_type == LDLM_IBITS)
 		ldlm_grant_lock_with_skiplist(lock);
 	else if (res->lr_type == LDLM_EXTENT)
 		ldlm_extent_add_lock(res, lock);
-	else
+	else if (res->lr_type == LDLM_FLOCK) {
+		/*
+		 * We should not add locks to granted list in the following cases:
+		 * - this is an UNLOCK but not a real lock;
+		 * - this is a TEST lock;
+		 * - this is a F_CANCELLK lock (async flock has req_mode == 0)
+		 * - this is a deadlock (flock cannot be granted)
+		 */
+		if (!lock->l_req_mode || lock->l_req_mode == LCK_NL ||
+		    ldlm_is_test_lock(lock) || ldlm_is_flock_deadlock(lock))
+			return;
 		ldlm_resource_add_lock(res, &res->lr_granted, lock);
-
-	if (work_list && lock->l_completion_ast)
-		ldlm_add_ast_work_item(lock, NULL, work_list);
+	} else
+		LBUG();
 
 	ldlm_pool_add(&ldlm_res_to_ns(res)->ns_pool, lock);
 }
@@ -1546,6 +1559,8 @@ enum ldlm_error ldlm_lock_enqueue(struct ldlm_namespace *ns,
 	 */
 	if (*flags & LDLM_FL_AST_DISCARD_DATA)
 		ldlm_set_ast_discard_data(lock);
+	if (*flags & LDLM_FL_TEST_LOCK)
+		ldlm_set_test_lock(lock);
 
 	/*
 	 * This distinction between local lock trees is very important; a client
diff --git a/drivers/staging/lustre/lustre/ldlm/ldlm_request.c b/drivers/staging/lustre/lustre/ldlm/ldlm_request.c
index af487f9..984a460 100644
--- a/drivers/staging/lustre/lustre/ldlm/ldlm_request.c
+++ b/drivers/staging/lustre/lustre/ldlm/ldlm_request.c
@@ -309,8 +309,6 @@ static void failed_lock_cleanup(struct ldlm_namespace *ns,
 	else
 		LDLM_DEBUG(lock, "lock was granted or failed in race");
 
-	ldlm_lock_decref_internal(lock, mode);
-
 	/* XXX - HACK because we shouldn't call ldlm_lock_destroy()
 	 *       from llite/file.c/ll_file_flock().
 	 */
@@ -321,9 +319,14 @@ static void failed_lock_cleanup(struct ldlm_namespace *ns,
 	 */
 	if (lock->l_resource->lr_type == LDLM_FLOCK) {
 		lock_res_and_lock(lock);
-		ldlm_resource_unlink_lock(lock);
-		ldlm_lock_destroy_nolock(lock);
+		if (!ldlm_is_destroyed(lock)) {
+			ldlm_resource_unlink_lock(lock);
+			ldlm_lock_decref_internal_nolock(lock, mode);
+			ldlm_lock_destroy_nolock(lock);
+		}
 		unlock_res_and_lock(lock);
+	} else {
+		ldlm_lock_decref_internal(lock, mode);
 	}
 }
 
@@ -418,11 +421,6 @@ int ldlm_cli_enqueue_fini(struct obd_export *exp, struct ptlrpc_request *req,
 	*flags = ldlm_flags_from_wire(reply->lock_flags);
 	lock->l_flags |= ldlm_flags_from_wire(reply->lock_flags &
 					      LDLM_FL_INHERIT_MASK);
-	/* move NO_TIMEOUT flag to the lock to force ldlm_lock_match()
-	 * to wait with no timeout as well
-	 */
-	lock->l_flags |= ldlm_flags_from_wire(reply->lock_flags &
-					      LDLM_FL_NO_TIMEOUT);
 	unlock_res_and_lock(lock);
 
 	CDEBUG(D_INFO, "local: %p, remote cookie: %#llx, flags: 0x%llx\n",
diff --git a/drivers/staging/lustre/lustre/ldlm/ldlm_resource.c b/drivers/staging/lustre/lustre/ldlm/ldlm_resource.c
index 51a28d9..5866b00 100644
--- a/drivers/staging/lustre/lustre/ldlm/ldlm_resource.c
+++ b/drivers/staging/lustre/lustre/ldlm/ldlm_resource.c
@@ -793,8 +793,14 @@ static void cleanup_resource(struct ldlm_resource *res, struct list_head *q,
 			 */
 			unlock_res(res);
 			LDLM_DEBUG(lock, "setting FL_LOCAL_ONLY");
+			if (lock->l_flags & LDLM_FL_FAIL_LOC) {
+				set_current_state(TASK_UNINTERRUPTIBLE);
+				schedule_timeout(cfs_time_seconds(4));
+				set_current_state(TASK_RUNNING);
+			}
 			if (lock->l_completion_ast)
-				lock->l_completion_ast(lock, 0, NULL);
+				lock->l_completion_ast(lock, LDLM_FL_FAILED,
+						       NULL);
 			LDLM_LOCK_RELEASE(lock);
 			continue;
 		}
diff --git a/drivers/staging/lustre/lustre/llite/file.c b/drivers/staging/lustre/lustre/llite/file.c
index 4e483c0..1452a14 100644
--- a/drivers/staging/lustre/lustre/llite/file.c
+++ b/drivers/staging/lustre/lustre/llite/file.c
@@ -2717,6 +2717,7 @@ ll_file_flock(struct file *file, int cmd, struct file_lock *file_lock)
 	struct md_op_data *op_data;
 	struct lustre_handle lockh = {0};
 	ldlm_policy_data_t flock = { {0} };
+	int fl_type = file_lock->fl_type;
 	__u64 flags = 0;
 	int rc;
 	int rc2 = 0;
@@ -2747,7 +2748,7 @@ ll_file_flock(struct file *file, int cmd, struct file_lock *file_lock)
 	if (file_lock->fl_lmops && file_lock->fl_lmops->lm_compare_owner)
 		flock.l_flock.owner = (unsigned long)file_lock->fl_pid;
 
-	switch (file_lock->fl_type) {
+	switch (fl_type) {
 	case F_RDLCK:
 		einfo.ei_mode = LCK_PR;
 		break;
@@ -2767,8 +2768,7 @@ ll_file_flock(struct file *file, int cmd, struct file_lock *file_lock)
 		einfo.ei_mode = LCK_PW;
 		break;
 	default:
-		CDEBUG(D_INFO, "Unknown fcntl lock type: %d\n",
-		       file_lock->fl_type);
+		CDEBUG(D_INFO, "Unknown fcntl lock type: %d\n", fl_type);
 		return -ENOTSUPP;
 	}
 
@@ -2790,16 +2790,18 @@ ll_file_flock(struct file *file, int cmd, struct file_lock *file_lock)
 	case F_GETLK64:
 #endif
 		flags = LDLM_FL_TEST_LOCK;
-		/* Save the old mode so that if the mode in the lock changes we
-		 * can decrement the appropriate reader or writer refcount.
-		 */
-		file_lock->fl_type = einfo.ei_mode;
 		break;
 	default:
 		CERROR("unknown fcntl lock command: %d\n", cmd);
 		return -EINVAL;
 	}
 
+	/*
+	 * Save the old mode so that if the mode in the lock changes we
+	 * can decrement the appropriate reader or writer refcount.
+	 */
+	file_lock->fl_type = einfo.ei_mode;
+
 	op_data = ll_prep_md_op_data(NULL, inode, NULL, NULL, 0, 0,
 				     LUSTRE_OPC_ANY, NULL);
 	if (IS_ERR(op_data))
@@ -2812,6 +2814,10 @@ ll_file_flock(struct file *file, int cmd, struct file_lock *file_lock)
 	rc = md_enqueue(sbi->ll_md_exp, &einfo, NULL,
 			op_data, &lockh, &flock, 0, NULL /* req */, flags);
 
+	/* Restore the file lock type if not TEST lock. */
+	if (!(flags & LDLM_FL_TEST_LOCK))
+		file_lock->fl_type = fl_type;
+
 	if ((rc == 0 || file_lock->fl_type == F_UNLCK) &&
 	    !(flags & LDLM_FL_TEST_LOCK))
 		rc2  = locks_lock_file_wait(file, file_lock);
-- 
1.7.1

[PATCH 56/58] staging: lustre: move ioctls to lustre_ioctl.h

[James Simmons]

From: John L. Hammond <john.hammond@intel.com>

Move ioctl definitions and related functions from lustre_dlm.h,
lustre_lib.h, obd.h, to lustre_ioctl.h. Replace the definitions of
retired ioctls with comment.

Signed-off-by: John L. Hammond <john.hammond@intel.com>
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-4961
Reviewed-on: http://review.whamcloud.com/10139
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Reviewed-by: Robert Read <robert.read@intel.com>
Signed-off-by: James Simmons <jsimmons@infradead.org>
---
 .../lustre/lustre/include/lustre/lustre_ioctl.h    |  412 ++++++++++++++++++++
 .../lustre/lustre/include/lustre/lustre_user.h     |   21 +-
 drivers/staging/lustre/lustre/include/lustre_dlm.h |   10 -
 drivers/staging/lustre/lustre/include/lustre_lib.h |  284 --------------
 drivers/staging/lustre/lustre/include/obd.h        |   10 -
 drivers/staging/lustre/lustre/llite/dir.c          |    9 +-
 drivers/staging/lustre/lustre/llite/file.c         |    1 +
 drivers/staging/lustre/lustre/llite/llite_lib.c    |    1 +
 drivers/staging/lustre/lustre/lmv/lmv_obd.c        |    1 +
 drivers/staging/lustre/lustre/lov/lov_obd.c        |    1 +
 drivers/staging/lustre/lustre/mdc/mdc_request.c    |    1 +
 drivers/staging/lustre/lustre/obdclass/class_obd.c |    8 +-
 .../lustre/lustre/obdclass/linux/linux-module.c    |    1 +
 .../staging/lustre/lustre/obdclass/obd_config.c    |    1 +
 .../staging/lustre/lustre/obdecho/echo_client.c    |    1 +
 drivers/staging/lustre/lustre/osc/osc_request.c    |    1 +
 16 files changed, 430 insertions(+), 333 deletions(-)
 create mode 100644 drivers/staging/lustre/lustre/include/lustre/lustre_ioctl.h

diff --git a/drivers/staging/lustre/lustre/include/lustre/lustre_ioctl.h b/drivers/staging/lustre/lustre/include/lustre/lustre_ioctl.h
new file mode 100644
index 0000000..f3d7c94
--- /dev/null
+++ b/drivers/staging/lustre/lustre/include/lustre/lustre_ioctl.h
@@ -0,0 +1,412 @@
+/*
+ * GPL HEADER START
+ *
+ * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 only,
+ * as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License version 2 for more details (a copy is included
+ * in the LICENSE file that accompanied this code).
+ *
+ * You should have received a copy of the GNU General Public License
+ * version 2 along with this program; If not, see
+ * http://www.gnu.org/licenses/gpl-2.0.html
+ *
+ * GPL HEADER END
+ */
+/*
+ * Copyright (c) 2007, 2010, Oracle and/or its affiliates. All rights reserved.
+ * Use is subject to license terms.
+ *
+ * Copyright (c) 2011, 2015, Intel Corporation.
+ */
+#ifndef LUSTRE_IOCTL_H_
+#define LUSTRE_IOCTL_H_
+
+#include <linux/types.h>
+#include "../../../include/linux/libcfs/libcfs.h"
+#include "lustre_idl.h"
+
+#ifdef __KERNEL__
+# include <linux/ioctl.h>
+# include <linux/string.h>
+# include "../obd_support.h"
+#else /* __KERNEL__ */
+# include <malloc.h>
+# include <string.h>
+#include <libcfs/util/ioctl.h>
+#endif /* !__KERNEL__ */
+
+#if !defined(__KERNEL__) && !defined(LUSTRE_UTILS)
+# error This file is for Lustre internal use only.
+#endif
+
+enum md_echo_cmd {
+	ECHO_MD_CREATE		= 1, /* Open/Create file on MDT */
+	ECHO_MD_MKDIR		= 2, /* Mkdir on MDT */
+	ECHO_MD_DESTROY		= 3, /* Unlink file on MDT */
+	ECHO_MD_RMDIR		= 4, /* Rmdir on MDT */
+	ECHO_MD_LOOKUP		= 5, /* Lookup on MDT */
+	ECHO_MD_GETATTR		= 6, /* Getattr on MDT */
+	ECHO_MD_SETATTR		= 7, /* Setattr on MDT */
+	ECHO_MD_ALLOC_FID	= 8, /* Get FIDs from MDT */
+};
+
+#define OBD_DEV_ID 1
+#define OBD_DEV_NAME "obd"
+#define OBD_DEV_PATH "/dev/" OBD_DEV_NAME
+#define OBD_DEV_MAJOR 10
+#define OBD_DEV_MINOR 241
+
+#define OBD_IOCTL_VERSION	0x00010004
+#define OBD_DEV_BY_DEVNAME	0xffffd0de
+#define OBD_MAX_IOCTL_BUFFER	CONFIG_LUSTRE_OBD_MAX_IOCTL_BUFFER
+
+struct obd_ioctl_data {
+	__u32		ioc_len;
+	__u32		ioc_version;
+
+	union {
+		__u64	ioc_cookie;
+		__u64	ioc_u64_1;
+	};
+	union {
+		__u32	ioc_conn1;
+		__u32	ioc_u32_1;
+	};
+	union {
+		__u32	ioc_conn2;
+		__u32	ioc_u32_2;
+	};
+
+	struct obdo	ioc_obdo1;
+	struct obdo	ioc_obdo2;
+
+	__u64		ioc_count;
+	__u64		ioc_offset;
+	__u32		ioc_dev;
+	__u32		ioc_command;
+
+	__u64		ioc_nid;
+	__u32		ioc_nal;
+	__u32		ioc_type;
+
+	/* buffers the kernel will treat as user pointers */
+	__u32		ioc_plen1;
+	char __user    *ioc_pbuf1;
+	__u32		ioc_plen2;
+	char __user    *ioc_pbuf2;
+
+	/* inline buffers for various arguments */
+	__u32		ioc_inllen1;
+	char	       *ioc_inlbuf1;
+	__u32		ioc_inllen2;
+	char	       *ioc_inlbuf2;
+	__u32		ioc_inllen3;
+	char	       *ioc_inlbuf3;
+	__u32		ioc_inllen4;
+	char	       *ioc_inlbuf4;
+
+	char		ioc_bulk[0];
+};
+
+struct obd_ioctl_hdr {
+	__u32		ioc_len;
+	__u32		ioc_version;
+};
+
+static inline __u32 obd_ioctl_packlen(struct obd_ioctl_data *data)
+{
+	__u32 len = cfs_size_round(sizeof(*data));
+
+	len += cfs_size_round(data->ioc_inllen1);
+	len += cfs_size_round(data->ioc_inllen2);
+	len += cfs_size_round(data->ioc_inllen3);
+	len += cfs_size_round(data->ioc_inllen4);
+
+	return len;
+}
+
+static inline int obd_ioctl_is_invalid(struct obd_ioctl_data *data)
+{
+	if (data->ioc_len > (1 << 30)) {
+		CERROR("OBD ioctl: ioc_len larger than 1<<30\n");
+		return 1;
+	}
+
+	if (data->ioc_inllen1 > (1 << 30)) {
+		CERROR("OBD ioctl: ioc_inllen1 larger than 1<<30\n");
+		return 1;
+	}
+
+	if (data->ioc_inllen2 > (1 << 30)) {
+		CERROR("OBD ioctl: ioc_inllen2 larger than 1<<30\n");
+		return 1;
+	}
+
+	if (data->ioc_inllen3 > (1 << 30)) {
+		CERROR("OBD ioctl: ioc_inllen3 larger than 1<<30\n");
+		return 1;
+	}
+
+	if (data->ioc_inllen4 > (1 << 30)) {
+		CERROR("OBD ioctl: ioc_inllen4 larger than 1<<30\n");
+		return 1;
+	}
+
+	if (data->ioc_inlbuf1 && !data->ioc_inllen1) {
+		CERROR("OBD ioctl: inlbuf1 pointer but 0 length\n");
+		return 1;
+	}
+
+	if (data->ioc_inlbuf2 && !data->ioc_inllen2) {
+		CERROR("OBD ioctl: inlbuf2 pointer but 0 length\n");
+		return 1;
+	}
+
+	if (data->ioc_inlbuf3 && !data->ioc_inllen3) {
+		CERROR("OBD ioctl: inlbuf3 pointer but 0 length\n");
+		return 1;
+	}
+
+	if (data->ioc_inlbuf4 && !data->ioc_inllen4) {
+		CERROR("OBD ioctl: inlbuf4 pointer but 0 length\n");
+		return 1;
+	}
+
+	if (data->ioc_pbuf1 && !data->ioc_plen1) {
+		CERROR("OBD ioctl: pbuf1 pointer but 0 length\n");
+		return 1;
+	}
+
+	if (data->ioc_pbuf2 && !data->ioc_plen2) {
+		CERROR("OBD ioctl: pbuf2 pointer but 0 length\n");
+		return 1;
+	}
+
+	if (!data->ioc_pbuf1 && data->ioc_plen1) {
+		CERROR("OBD ioctl: plen1 set but NULL pointer\n");
+		return 1;
+	}
+
+	if (!data->ioc_pbuf2 && data->ioc_plen2) {
+		CERROR("OBD ioctl: plen2 set but NULL pointer\n");
+		return 1;
+	}
+
+	if (obd_ioctl_packlen(data) > data->ioc_len) {
+		CERROR("OBD ioctl: packlen exceeds ioc_len (%d > %d)\n",
+		       obd_ioctl_packlen(data), data->ioc_len);
+		return 1;
+	}
+
+	return 0;
+}
+
+#ifdef __KERNEL__
+
+int obd_ioctl_getdata(char **buf, int *len, void __user *arg);
+int obd_ioctl_popdata(void __user *arg, void *data, int len);
+
+static inline void obd_ioctl_freedata(char *buf, size_t len)
+{
+	kvfree(buf);
+}
+
+#else /* __KERNEL__ */
+
+static inline int obd_ioctl_pack(struct obd_ioctl_data *data, char **pbuf,
+				 int max_len)
+{
+	char *ptr;
+	struct obd_ioctl_data *overlay;
+
+	data->ioc_len = obd_ioctl_packlen(data);
+	data->ioc_version = OBD_IOCTL_VERSION;
+
+	if (*pbuf && data->ioc_len > max_len) {
+		fprintf(stderr, "pbuf = %p, ioc_len = %u, max_len = %d\n",
+			*pbuf, data->ioc_len, max_len);
+		return -EINVAL;
+	}
+
+	if (!*pbuf)
+		*pbuf = malloc(data->ioc_len);
+
+	if (!*pbuf)
+		return -ENOMEM;
+
+	overlay = (struct obd_ioctl_data *)*pbuf;
+	memcpy(*pbuf, data, sizeof(*data));
+
+	ptr = overlay->ioc_bulk;
+	if (data->ioc_inlbuf1)
+		LOGL(data->ioc_inlbuf1, data->ioc_inllen1, ptr);
+
+	if (data->ioc_inlbuf2)
+		LOGL(data->ioc_inlbuf2, data->ioc_inllen2, ptr);
+
+	if (data->ioc_inlbuf3)
+		LOGL(data->ioc_inlbuf3, data->ioc_inllen3, ptr);
+
+	if (data->ioc_inlbuf4)
+		LOGL(data->ioc_inlbuf4, data->ioc_inllen4, ptr);
+
+	if (obd_ioctl_is_invalid(overlay)) {
+		fprintf(stderr, "invalid ioctl data: ioc_len = %u, max_len = %d\n",
+			data->ioc_len, max_len);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static inline int
+obd_ioctl_unpack(struct obd_ioctl_data *data, char *pbuf, int max_len)
+{
+	char *ptr;
+	struct obd_ioctl_data *overlay;
+
+	if (!pbuf)
+		return 1;
+
+	overlay = (struct obd_ioctl_data *)pbuf;
+
+	/* Preserve the caller's buffer pointers */
+	overlay->ioc_inlbuf1 = data->ioc_inlbuf1;
+	overlay->ioc_inlbuf2 = data->ioc_inlbuf2;
+	overlay->ioc_inlbuf3 = data->ioc_inlbuf3;
+	overlay->ioc_inlbuf4 = data->ioc_inlbuf4;
+
+	memcpy(data, pbuf, sizeof(*data));
+
+	ptr = overlay->ioc_bulk;
+	if (data->ioc_inlbuf1)
+		LOGU(data->ioc_inlbuf1, data->ioc_inllen1, ptr);
+
+	if (data->ioc_inlbuf2)
+		LOGU(data->ioc_inlbuf2, data->ioc_inllen2, ptr);
+
+	if (data->ioc_inlbuf3)
+		LOGU(data->ioc_inlbuf3, data->ioc_inllen3, ptr);
+
+	if (data->ioc_inlbuf4)
+		LOGU(data->ioc_inlbuf4, data->ioc_inllen4, ptr);
+
+	return 0;
+}
+
+#endif /* !__KERNEL__ */
+
+/*
+ * OBD_IOC_DATA_TYPE is only for compatibility reasons with older
+ * Linux Lustre user tools. New ioctls should NOT use this macro as
+ * the ioctl "size". Instead the ioctl should get a "size" argument
+ * which is the actual data type used by the ioctl, to ensure the
+ * ioctl interface is versioned correctly.
+ */
+#define OBD_IOC_DATA_TYPE	long
+
+/*	IOC_LDLM_TEST		_IOWR('f', 40, long) */
+/*	IOC_LDLM_DUMP		_IOWR('f', 41, long) */
+/*	IOC_LDLM_REGRESS_START	_IOWR('f', 42, long) */
+/*	IOC_LDLM_REGRESS_STOP	_IOWR('f', 43, long) */
+
+#define OBD_IOC_CREATE		_IOWR('f', 101, OBD_IOC_DATA_TYPE)
+#define OBD_IOC_DESTROY		_IOW('f', 104, OBD_IOC_DATA_TYPE)
+/*	OBD_IOC_PREALLOCATE	_IOWR('f', 105, OBD_IOC_DATA_TYPE) */
+
+#define OBD_IOC_SETATTR		_IOW('f', 107, OBD_IOC_DATA_TYPE)
+#define OBD_IOC_GETATTR		_IOWR('f', 108, OBD_IOC_DATA_TYPE)
+#define OBD_IOC_READ		_IOWR('f', 109, OBD_IOC_DATA_TYPE)
+#define OBD_IOC_WRITE		_IOWR('f', 110, OBD_IOC_DATA_TYPE)
+
+#define OBD_IOC_STATFS		_IOWR('f', 113, OBD_IOC_DATA_TYPE)
+#define OBD_IOC_SYNC		_IOW('f', 114, OBD_IOC_DATA_TYPE)
+/*	OBD_IOC_READ2		_IOWR('f', 115, OBD_IOC_DATA_TYPE) */
+/*	OBD_IOC_FORMAT		_IOWR('f', 116, OBD_IOC_DATA_TYPE) */
+/*	OBD_IOC_PARTITION	_IOWR('f', 117, OBD_IOC_DATA_TYPE) */
+/*	OBD_IOC_COPY		_IOWR('f', 120, OBD_IOC_DATA_TYPE) */
+/*	OBD_IOC_MIGR		_IOWR('f', 121, OBD_IOC_DATA_TYPE) */
+/*	OBD_IOC_PUNCH		_IOWR('f', 122, OBD_IOC_DATA_TYPE) */
+
+/*	OBD_IOC_MODULE_DEBUG	_IOWR('f', 124, OBD_IOC_DATA_TYPE) */
+#define OBD_IOC_BRW_READ	_IOWR('f', 125, OBD_IOC_DATA_TYPE)
+#define OBD_IOC_BRW_WRITE	_IOWR('f', 126, OBD_IOC_DATA_TYPE)
+#define OBD_IOC_NAME2DEV	_IOWR('f', 127, OBD_IOC_DATA_TYPE)
+#define OBD_IOC_UUID2DEV	_IOWR('f', 130, OBD_IOC_DATA_TYPE)
+#define OBD_IOC_GETNAME		_IOWR('f', 131, OBD_IOC_DATA_TYPE)
+#define OBD_IOC_GETMDNAME	_IOR('f', 131, char[MAX_OBD_NAME])
+#define OBD_IOC_GETDTNAME	OBD_IOC_GETNAME
+#define OBD_IOC_LOV_GET_CONFIG	_IOWR('f', 132, OBD_IOC_DATA_TYPE)
+#define OBD_IOC_CLIENT_RECOVER	_IOW('f', 133, OBD_IOC_DATA_TYPE)
+#define OBD_IOC_PING_TARGET	_IOW('f', 136, OBD_IOC_DATA_TYPE)
+
+/*	OBD_IOC_DEC_FS_USE_COUNT _IO('f', 139) */
+#define OBD_IOC_NO_TRANSNO	_IOW('f', 140, OBD_IOC_DATA_TYPE)
+#define OBD_IOC_SET_READONLY	_IOW('f', 141, OBD_IOC_DATA_TYPE)
+#define OBD_IOC_ABORT_RECOVERY	_IOR('f', 142, OBD_IOC_DATA_TYPE)
+/*	OBD_IOC_ROOT_SQUASH	_IOWR('f', 143, OBD_IOC_DATA_TYPE) */
+#define OBD_GET_VERSION		_IOWR('f', 144, OBD_IOC_DATA_TYPE)
+/*	OBD_IOC_GSS_SUPPORT	_IOWR('f', 145, OBD_IOC_DATA_TYPE) */
+/*	OBD_IOC_CLOSE_UUID	_IOWR('f', 147, OBD_IOC_DATA_TYPE) */
+#define OBD_IOC_CHANGELOG_SEND	_IOW('f', 148, OBD_IOC_DATA_TYPE)
+#define OBD_IOC_GETDEVICE	_IOWR('f', 149, OBD_IOC_DATA_TYPE)
+#define OBD_IOC_FID2PATH	_IOWR('f', 150, OBD_IOC_DATA_TYPE)
+/*	lustre/lustre_user.h	151-153 */
+/*	OBD_IOC_LOV_SETSTRIPE	154 LL_IOC_LOV_SETSTRIPE */
+/*	OBD_IOC_LOV_GETSTRIPE	155 LL_IOC_LOV_GETSTRIPE */
+/*	OBD_IOC_LOV_SETEA	156 LL_IOC_LOV_SETEA */
+/*	lustre/lustre_user.h	157-159 */
+#define	OBD_IOC_QUOTACHECK	_IOW('f', 160, int)
+#define	OBD_IOC_POLL_QUOTACHECK	_IOR('f', 161, struct if_quotacheck *)
+#define OBD_IOC_QUOTACTL	_IOWR('f', 162, struct if_quotactl)
+/*	lustre/lustre_user.h	163-176 */
+#define OBD_IOC_CHANGELOG_REG	_IOW('f', 177, struct obd_ioctl_data)
+#define OBD_IOC_CHANGELOG_DEREG	_IOW('f', 178, struct obd_ioctl_data)
+#define OBD_IOC_CHANGELOG_CLEAR	_IOW('f', 179, struct obd_ioctl_data)
+/*	OBD_IOC_RECORD		_IOWR('f', 180, OBD_IOC_DATA_TYPE) */
+/*	OBD_IOC_ENDRECORD	_IOWR('f', 181, OBD_IOC_DATA_TYPE) */
+/*	OBD_IOC_PARSE		_IOWR('f', 182, OBD_IOC_DATA_TYPE) */
+/*	OBD_IOC_DORECORD	_IOWR('f', 183, OBD_IOC_DATA_TYPE) */
+#define OBD_IOC_PROCESS_CFG	_IOWR('f', 184, OBD_IOC_DATA_TYPE)
+/*	OBD_IOC_DUMP_LOG	_IOWR('f', 185, OBD_IOC_DATA_TYPE) */
+/*	OBD_IOC_CLEAR_LOG	_IOWR('f', 186, OBD_IOC_DATA_TYPE) */
+#define OBD_IOC_PARAM		_IOW('f', 187, OBD_IOC_DATA_TYPE)
+#define OBD_IOC_POOL		_IOWR('f', 188, OBD_IOC_DATA_TYPE)
+#define OBD_IOC_REPLACE_NIDS	_IOWR('f', 189, OBD_IOC_DATA_TYPE)
+
+#define OBD_IOC_CATLOGLIST	_IOWR('f', 190, OBD_IOC_DATA_TYPE)
+#define OBD_IOC_LLOG_INFO	_IOWR('f', 191, OBD_IOC_DATA_TYPE)
+#define OBD_IOC_LLOG_PRINT	_IOWR('f', 192, OBD_IOC_DATA_TYPE)
+#define OBD_IOC_LLOG_CANCEL	_IOWR('f', 193, OBD_IOC_DATA_TYPE)
+#define OBD_IOC_LLOG_REMOVE	_IOWR('f', 194, OBD_IOC_DATA_TYPE)
+#define OBD_IOC_LLOG_CHECK	_IOWR('f', 195, OBD_IOC_DATA_TYPE)
+/*	OBD_IOC_LLOG_CATINFO	_IOWR('f', 196, OBD_IOC_DATA_TYPE) */
+#define OBD_IOC_NODEMAP		_IOWR('f', 197, OBD_IOC_DATA_TYPE)
+
+/*	ECHO_IOC_GET_STRIPE	_IOWR('f', 200, OBD_IOC_DATA_TYPE) */
+/*	ECHO_IOC_SET_STRIPE	_IOWR('f', 201, OBD_IOC_DATA_TYPE) */
+/*	ECHO_IOC_ENQUEUE	_IOWR('f', 202, OBD_IOC_DATA_TYPE) */
+/*	ECHO_IOC_CANCEL		_IOWR('f', 203, OBD_IOC_DATA_TYPE) */
+
+#define OBD_IOC_GET_OBJ_VERSION	_IOR('f', 210, OBD_IOC_DATA_TYPE)
+
+/*	lustre/lustre_user.h	212-217 */
+#define OBD_IOC_GET_MNTOPT	_IOW('f', 220, mntopt_t)
+#define OBD_IOC_ECHO_MD		_IOR('f', 221, struct obd_ioctl_data)
+#define OBD_IOC_ECHO_ALLOC_SEQ	_IOWR('f', 222, struct obd_ioctl_data)
+#define OBD_IOC_START_LFSCK	_IOWR('f', 230, OBD_IOC_DATA_TYPE)
+#define OBD_IOC_STOP_LFSCK	_IOW('f', 231, OBD_IOC_DATA_TYPE)
+#define OBD_IOC_QUERY_LFSCK	_IOR('f', 232, struct obd_ioctl_data)
+/*	lustre/lustre_user.h	240-249 */
+/*	LIBCFS_IOC_DEBUG_MASK	250 */
+
+#define IOC_OSC_SET_ACTIVE	_IOWR('h', 21, void *)
+
+#endif /* LUSTRE_IOCTL_H_ */
diff --git a/drivers/staging/lustre/lustre/include/lustre/lustre_user.h b/drivers/staging/lustre/lustre/include/lustre/lustre_user.h
index 4746320..75a78a3 100644
--- a/drivers/staging/lustre/lustre/include/lustre/lustre_user.h
+++ b/drivers/staging/lustre/lustre/include/lustre/lustre_user.h
@@ -188,26 +188,20 @@ struct ost_id {
  * *STRIPE* - set/get lov_user_md
  * *INFO    - set/get lov_user_mds_data
  */
-/* see <lustre_lib.h> for ioctl numberss 101-150 */
+/*	lustre_ioctl.h			101-150 */
 #define LL_IOC_GETFLAGS		 _IOR('f', 151, long)
 #define LL_IOC_SETFLAGS		 _IOW('f', 152, long)
 #define LL_IOC_CLRFLAGS		 _IOW('f', 153, long)
-/* LL_IOC_LOV_SETSTRIPE: See also OBD_IOC_LOV_SETSTRIPE */
 #define LL_IOC_LOV_SETSTRIPE	    _IOW('f', 154, long)
-/* LL_IOC_LOV_GETSTRIPE: See also OBD_IOC_LOV_GETSTRIPE */
 #define LL_IOC_LOV_GETSTRIPE	    _IOW('f', 155, long)
-/* LL_IOC_LOV_SETEA: See also OBD_IOC_LOV_SETEA */
 #define LL_IOC_LOV_SETEA		_IOW('f', 156, long)
 #define LL_IOC_RECREATE_OBJ	     _IOW('f', 157, long)
 #define LL_IOC_RECREATE_FID	     _IOW('f', 157, struct lu_fid)
 #define LL_IOC_GROUP_LOCK	       _IOW('f', 158, long)
 #define LL_IOC_GROUP_UNLOCK	     _IOW('f', 159, long)
-/* LL_IOC_QUOTACHECK: See also OBD_IOC_QUOTACHECK */
-#define LL_IOC_QUOTACHECK	       _IOW('f', 160, int)
-/* LL_IOC_POLL_QUOTACHECK: See also OBD_IOC_POLL_QUOTACHECK */
-#define LL_IOC_POLL_QUOTACHECK	  _IOR('f', 161, struct if_quotacheck *)
-/* LL_IOC_QUOTACTL: See also OBD_IOC_QUOTACTL */
-#define LL_IOC_QUOTACTL		 _IOWR('f', 162, struct if_quotactl)
+/* #define LL_IOC_QUOTACHECK		160 OBD_IOC_QUOTACHECK */
+/* #define LL_IOC_POLL_QUOTACHECK	161 OBD_IOC_POLL_QUOTACHECK */
+/* #define LL_IOC_QUOTACTL		162 OBD_IOC_QUOTACTL */
 #define IOC_OBD_STATFS		  _IOWR('f', 164, struct obd_statfs *)
 #define IOC_LOV_GETINFO		 _IOWR('f', 165, struct lov_user_mds_data *)
 #define LL_IOC_FLUSHCTX		 _IOW('f', 166, long)
@@ -221,8 +215,7 @@ struct ost_id {
 #define LL_IOC_GET_CONNECT_FLAGS	_IOWR('f', 174, __u64 *)
 #define LL_IOC_GET_MDTIDX	       _IOR('f', 175, int)
 
-/* see <lustre_lib.h> for ioctl numbers 177-210 */
-
+/*	lustre_ioctl.h			177-210 */
 #define LL_IOC_HSM_STATE_GET		_IOR('f', 211, struct hsm_user_state)
 #define LL_IOC_HSM_STATE_SET		_IOW('f', 212, struct hsm_state_set)
 #define LL_IOC_HSM_CT_START		_IOW('f', 213, struct lustre_kernelcomm)
@@ -255,10 +248,6 @@ struct ost_id {
 #define IOC_MDC_GETFILEINFO     _IOWR(IOC_MDC_TYPE, 22, struct lov_user_mds_data *)
 #define LL_IOC_MDC_GETINFO      _IOWR(IOC_MDC_TYPE, 23, struct lov_user_mds_data *)
 
-/* Keep these for backward compartability. */
-#define LL_IOC_OBD_STATFS       IOC_OBD_STATFS
-#define IOC_MDC_GETSTRIPE       IOC_MDC_GETFILESTRIPE
-
 #define MAX_OBD_NAME 128 /* If this changes, a NEW ioctl must be added */
 
 /* Define O_LOV_DELAY_CREATE to be a mask that is not useful for regular
diff --git a/drivers/staging/lustre/lustre/include/lustre_dlm.h b/drivers/staging/lustre/lustre/include/lustre_dlm.h
index f7805cc..1ec4231 100644
--- a/drivers/staging/lustre/lustre/include/lustre_dlm.h
+++ b/drivers/staging/lustre/lustre/include/lustre_dlm.h
@@ -1282,16 +1282,6 @@ int ldlm_cli_cancel_list(struct list_head *head, int count,
 int intent_disposition(struct ldlm_reply *rep, int flag);
 void intent_set_disposition(struct ldlm_reply *rep, int flag);
 
-/* ioctls for trying requests */
-#define IOC_LDLM_TYPE		   'f'
-#define IOC_LDLM_MIN_NR		 40
-
-#define IOC_LDLM_TEST		   _IOWR('f', 40, long)
-#define IOC_LDLM_DUMP		   _IOWR('f', 41, long)
-#define IOC_LDLM_REGRESS_START	  _IOWR('f', 42, long)
-#define IOC_LDLM_REGRESS_STOP	   _IOWR('f', 43, long)
-#define IOC_LDLM_MAX_NR		 43
-
 /**
  * "Modes" of acquiring lock_res, necessary to tell lockdep that taking more
  * than one lock_res is dead-lock safe.
diff --git a/drivers/staging/lustre/lustre/include/lustre_lib.h b/drivers/staging/lustre/lustre/include/lustre_lib.h
index def0193..adb8c47 100644
--- a/drivers/staging/lustre/lustre/include/lustre_lib.h
+++ b/drivers/staging/lustre/lustre/include/lustre_lib.h
@@ -75,7 +75,6 @@ int do_set_info_async(struct obd_import *imp,
 		      struct ptlrpc_request_set *set);
 
 #define OBD_RECOVERY_MAX_TIME (obd_timeout * 18) /* b13079 */
-#define OBD_MAX_IOCTL_BUFFER CONFIG_LUSTRE_OBD_MAX_IOCTL_BUFFER
 
 void target_send_reply(struct ptlrpc_request *req, int rc, int fail_id);
 
@@ -99,289 +98,6 @@ struct obd_client_handle {
 /* statfs_pack.c */
 void statfs_unpack(struct kstatfs *sfs, struct obd_statfs *osfs);
 
-/*
- * For md echo client
- */
-enum md_echo_cmd {
-	ECHO_MD_CREATE       = 1, /* Open/Create file on MDT */
-	ECHO_MD_MKDIR	= 2, /* Mkdir on MDT */
-	ECHO_MD_DESTROY      = 3, /* Unlink file on MDT */
-	ECHO_MD_RMDIR	= 4, /* Rmdir on MDT */
-	ECHO_MD_LOOKUP       = 5, /* Lookup on MDT */
-	ECHO_MD_GETATTR      = 6, /* Getattr on MDT */
-	ECHO_MD_SETATTR      = 7, /* Setattr on MDT */
-	ECHO_MD_ALLOC_FID    = 8, /* Get FIDs from MDT */
-};
-
-/*
- *   OBD IOCTLS
- */
-#define OBD_IOCTL_VERSION 0x00010004
-
-struct obd_ioctl_data {
-	__u32 ioc_len;
-	__u32 ioc_version;
-
-	union {
-		__u64 ioc_cookie;
-		__u64 ioc_u64_1;
-	};
-	union {
-		__u32 ioc_conn1;
-		__u32 ioc_u32_1;
-	};
-	union {
-		__u32 ioc_conn2;
-		__u32 ioc_u32_2;
-	};
-
-	struct obdo ioc_obdo1;
-	struct obdo ioc_obdo2;
-
-	u64	 ioc_count;
-	u64	 ioc_offset;
-	__u32    ioc_dev;
-	__u32    ioc_command;
-
-	__u64 ioc_nid;
-	__u32 ioc_nal;
-	__u32 ioc_type;
-
-	/* buffers the kernel will treat as user pointers */
-	__u32  ioc_plen1;
-	void __user *ioc_pbuf1;
-	__u32  ioc_plen2;
-	void __user *ioc_pbuf2;
-
-	/* inline buffers for various arguments */
-	__u32  ioc_inllen1;
-	char  *ioc_inlbuf1;
-	__u32  ioc_inllen2;
-	char  *ioc_inlbuf2;
-	__u32  ioc_inllen3;
-	char  *ioc_inlbuf3;
-	__u32  ioc_inllen4;
-	char  *ioc_inlbuf4;
-
-	char    ioc_bulk[0];
-};
-
-struct obd_ioctl_hdr {
-	__u32 ioc_len;
-	__u32 ioc_version;
-};
-
-static inline int obd_ioctl_packlen(struct obd_ioctl_data *data)
-{
-	int len = cfs_size_round(sizeof(struct obd_ioctl_data));
-
-	len += cfs_size_round(data->ioc_inllen1);
-	len += cfs_size_round(data->ioc_inllen2);
-	len += cfs_size_round(data->ioc_inllen3);
-	len += cfs_size_round(data->ioc_inllen4);
-	return len;
-}
-
-static inline int obd_ioctl_is_invalid(struct obd_ioctl_data *data)
-{
-	if (data->ioc_len > OBD_MAX_IOCTL_BUFFER) {
-		CERROR("OBD ioctl: ioc_len larger than %d\n",
-		       OBD_MAX_IOCTL_BUFFER);
-		return 1;
-	}
-	if (data->ioc_inllen1 > OBD_MAX_IOCTL_BUFFER) {
-		CERROR("OBD ioctl: ioc_inllen1 larger than ioc_len\n");
-		return 1;
-	}
-	if (data->ioc_inllen2 > OBD_MAX_IOCTL_BUFFER) {
-		CERROR("OBD ioctl: ioc_inllen2 larger than ioc_len\n");
-		return 1;
-	}
-	if (data->ioc_inllen3 > OBD_MAX_IOCTL_BUFFER) {
-		CERROR("OBD ioctl: ioc_inllen3 larger than ioc_len\n");
-		return 1;
-	}
-	if (data->ioc_inllen4 > OBD_MAX_IOCTL_BUFFER) {
-		CERROR("OBD ioctl: ioc_inllen4 larger than ioc_len\n");
-		return 1;
-	}
-	if (data->ioc_inlbuf1 && !data->ioc_inllen1) {
-		CERROR("OBD ioctl: inlbuf1 pointer but 0 length\n");
-		return 1;
-	}
-	if (data->ioc_inlbuf2 && !data->ioc_inllen2) {
-		CERROR("OBD ioctl: inlbuf2 pointer but 0 length\n");
-		return 1;
-	}
-	if (data->ioc_inlbuf3 && !data->ioc_inllen3) {
-		CERROR("OBD ioctl: inlbuf3 pointer but 0 length\n");
-		return 1;
-	}
-	if (data->ioc_inlbuf4 && !data->ioc_inllen4) {
-		CERROR("OBD ioctl: inlbuf4 pointer but 0 length\n");
-		return 1;
-	}
-	if (data->ioc_pbuf1 && !data->ioc_plen1) {
-		CERROR("OBD ioctl: pbuf1 pointer but 0 length\n");
-		return 1;
-	}
-	if (data->ioc_pbuf2 && !data->ioc_plen2) {
-		CERROR("OBD ioctl: pbuf2 pointer but 0 length\n");
-		return 1;
-	}
-	if (data->ioc_plen1 && !data->ioc_pbuf1) {
-		CERROR("OBD ioctl: plen1 set but NULL pointer\n");
-		return 1;
-	}
-	if (data->ioc_plen2 && !data->ioc_pbuf2) {
-		CERROR("OBD ioctl: plen2 set but NULL pointer\n");
-		return 1;
-	}
-	if (obd_ioctl_packlen(data) > data->ioc_len) {
-		CERROR("OBD ioctl: packlen exceeds ioc_len (%d > %d)\n",
-		       obd_ioctl_packlen(data), data->ioc_len);
-		return 1;
-	}
-	return 0;
-}
-
-#include "obd_support.h"
-
-/* function defined in lustre/obdclass/<platform>/<platform>-module.c */
-int obd_ioctl_getdata(char **buf, int *len, void __user *arg);
-int obd_ioctl_popdata(void __user *arg, void *data, int len);
-
-static inline void obd_ioctl_freedata(char *buf, int len)
-{
-	kvfree(buf);
-	return;
-}
-
-/*
- * BSD ioctl description:
- * #define IOC_V1       _IOR(g, n1, long)
- * #define IOC_V2       _IOW(g, n2, long)
- *
- * ioctl(f, IOC_V1, arg);
- * arg will be treated as a long value,
- *
- * ioctl(f, IOC_V2, arg)
- * arg will be treated as a pointer, bsd will call
- * copyin(buf, arg, sizeof(long))
- *
- * To make BSD ioctl handles argument correctly and simplely,
- * we change _IOR to _IOWR so BSD will copyin obd_ioctl_data
- * for us. Does this change affect Linux?  (XXX Liang)
- */
-#define OBD_IOC_DATA_TYPE long
-
-#define OBD_IOC_CREATE		 _IOWR('f', 101, OBD_IOC_DATA_TYPE)
-#define OBD_IOC_DESTROY		_IOW('f', 104, OBD_IOC_DATA_TYPE)
-#define OBD_IOC_PREALLOCATE	    _IOWR('f', 105, OBD_IOC_DATA_TYPE)
-
-#define OBD_IOC_SETATTR		_IOW('f', 107, OBD_IOC_DATA_TYPE)
-#define OBD_IOC_GETATTR		_IOWR ('f', 108, OBD_IOC_DATA_TYPE)
-#define OBD_IOC_READ		   _IOWR('f', 109, OBD_IOC_DATA_TYPE)
-#define OBD_IOC_WRITE		  _IOWR('f', 110, OBD_IOC_DATA_TYPE)
-
-#define OBD_IOC_STATFS		 _IOWR('f', 113, OBD_IOC_DATA_TYPE)
-#define OBD_IOC_SYNC		   _IOW('f', 114, OBD_IOC_DATA_TYPE)
-#define OBD_IOC_READ2		  _IOWR('f', 115, OBD_IOC_DATA_TYPE)
-#define OBD_IOC_FORMAT		 _IOWR('f', 116, OBD_IOC_DATA_TYPE)
-#define OBD_IOC_PARTITION	      _IOWR('f', 117, OBD_IOC_DATA_TYPE)
-#define OBD_IOC_COPY		   _IOWR('f', 120, OBD_IOC_DATA_TYPE)
-#define OBD_IOC_MIGR		   _IOWR('f', 121, OBD_IOC_DATA_TYPE)
-#define OBD_IOC_PUNCH		  _IOWR('f', 122, OBD_IOC_DATA_TYPE)
-
-#define OBD_IOC_MODULE_DEBUG	   _IOWR('f', 124, OBD_IOC_DATA_TYPE)
-#define OBD_IOC_BRW_READ	       _IOWR('f', 125, OBD_IOC_DATA_TYPE)
-#define OBD_IOC_BRW_WRITE	      _IOWR('f', 126, OBD_IOC_DATA_TYPE)
-#define OBD_IOC_NAME2DEV	       _IOWR('f', 127, OBD_IOC_DATA_TYPE)
-#define OBD_IOC_UUID2DEV	       _IOWR('f', 130, OBD_IOC_DATA_TYPE)
-
-#define OBD_IOC_GETNAME		_IOWR('f', 131, OBD_IOC_DATA_TYPE)
-#define OBD_IOC_GETMDNAME	      _IOR('f', 131, char[MAX_OBD_NAME])
-#define OBD_IOC_GETDTNAME	       OBD_IOC_GETNAME
-
-#define OBD_IOC_LOV_GET_CONFIG	 _IOWR('f', 132, OBD_IOC_DATA_TYPE)
-#define OBD_IOC_CLIENT_RECOVER	 _IOW('f', 133, OBD_IOC_DATA_TYPE)
-#define OBD_IOC_PING_TARGET	    _IOW('f', 136, OBD_IOC_DATA_TYPE)
-
-#define OBD_IOC_DEC_FS_USE_COUNT       _IO  ('f', 139)
-#define OBD_IOC_NO_TRANSNO	     _IOW('f', 140, OBD_IOC_DATA_TYPE)
-#define OBD_IOC_SET_READONLY	   _IOW('f', 141, OBD_IOC_DATA_TYPE)
-#define OBD_IOC_ABORT_RECOVERY	 _IOR('f', 142, OBD_IOC_DATA_TYPE)
-
-#define OBD_IOC_ROOT_SQUASH	    _IOWR('f', 143, OBD_IOC_DATA_TYPE)
-
-#define OBD_GET_VERSION		_IOWR ('f', 144, OBD_IOC_DATA_TYPE)
-
-#define OBD_IOC_GSS_SUPPORT	    _IOWR('f', 145, OBD_IOC_DATA_TYPE)
-
-#define OBD_IOC_CLOSE_UUID	     _IOWR ('f', 147, OBD_IOC_DATA_TYPE)
-
-#define OBD_IOC_CHANGELOG_SEND	 _IOW('f', 148, OBD_IOC_DATA_TYPE)
-#define OBD_IOC_GETDEVICE	      _IOWR ('f', 149, OBD_IOC_DATA_TYPE)
-#define OBD_IOC_FID2PATH	       _IOWR ('f', 150, OBD_IOC_DATA_TYPE)
-/* see also <lustre/lustre_user.h> for ioctls 151-153 */
-/* OBD_IOC_LOV_SETSTRIPE: See also LL_IOC_LOV_SETSTRIPE */
-#define OBD_IOC_LOV_SETSTRIPE	  _IOW('f', 154, OBD_IOC_DATA_TYPE)
-/* OBD_IOC_LOV_GETSTRIPE: See also LL_IOC_LOV_GETSTRIPE */
-#define OBD_IOC_LOV_GETSTRIPE	  _IOW('f', 155, OBD_IOC_DATA_TYPE)
-/* OBD_IOC_LOV_SETEA: See also LL_IOC_LOV_SETEA */
-#define OBD_IOC_LOV_SETEA	      _IOW('f', 156, OBD_IOC_DATA_TYPE)
-/* see <lustre/lustre_user.h> for ioctls 157-159 */
-/* OBD_IOC_QUOTACHECK: See also LL_IOC_QUOTACHECK */
-#define OBD_IOC_QUOTACHECK	     _IOW('f', 160, int)
-/* OBD_IOC_POLL_QUOTACHECK: See also LL_IOC_POLL_QUOTACHECK */
-#define OBD_IOC_POLL_QUOTACHECK	_IOR('f', 161, struct if_quotacheck *)
-/* OBD_IOC_QUOTACTL: See also LL_IOC_QUOTACTL */
-#define OBD_IOC_QUOTACTL	       _IOWR('f', 162, struct if_quotactl)
-/* see  also <lustre/lustre_user.h> for ioctls 163-176 */
-#define OBD_IOC_CHANGELOG_REG	  _IOW('f', 177, struct obd_ioctl_data)
-#define OBD_IOC_CHANGELOG_DEREG	_IOW('f', 178, struct obd_ioctl_data)
-#define OBD_IOC_CHANGELOG_CLEAR	_IOW('f', 179, struct obd_ioctl_data)
-#define OBD_IOC_RECORD		 _IOWR('f', 180, OBD_IOC_DATA_TYPE)
-#define OBD_IOC_ENDRECORD	      _IOWR('f', 181, OBD_IOC_DATA_TYPE)
-#define OBD_IOC_PARSE		  _IOWR('f', 182, OBD_IOC_DATA_TYPE)
-#define OBD_IOC_DORECORD	       _IOWR('f', 183, OBD_IOC_DATA_TYPE)
-#define OBD_IOC_PROCESS_CFG	    _IOWR('f', 184, OBD_IOC_DATA_TYPE)
-#define OBD_IOC_DUMP_LOG	       _IOWR('f', 185, OBD_IOC_DATA_TYPE)
-#define OBD_IOC_CLEAR_LOG	      _IOWR('f', 186, OBD_IOC_DATA_TYPE)
-#define OBD_IOC_PARAM		  _IOW('f', 187, OBD_IOC_DATA_TYPE)
-#define OBD_IOC_POOL		   _IOWR('f', 188, OBD_IOC_DATA_TYPE)
-#define OBD_IOC_REPLACE_NIDS	   _IOWR('f', 189, OBD_IOC_DATA_TYPE)
-
-#define OBD_IOC_CATLOGLIST	     _IOWR('f', 190, OBD_IOC_DATA_TYPE)
-#define OBD_IOC_LLOG_INFO	      _IOWR('f', 191, OBD_IOC_DATA_TYPE)
-#define OBD_IOC_LLOG_PRINT	     _IOWR('f', 192, OBD_IOC_DATA_TYPE)
-#define OBD_IOC_LLOG_CANCEL	    _IOWR('f', 193, OBD_IOC_DATA_TYPE)
-#define OBD_IOC_LLOG_REMOVE	    _IOWR('f', 194, OBD_IOC_DATA_TYPE)
-#define OBD_IOC_LLOG_CHECK	     _IOWR('f', 195, OBD_IOC_DATA_TYPE)
-/* OBD_IOC_LLOG_CATINFO is deprecated */
-#define OBD_IOC_LLOG_CATINFO	   _IOWR('f', 196, OBD_IOC_DATA_TYPE)
-
-/*	#define ECHO_IOC_GET_STRIPE    _IOWR('f', 200, OBD_IOC_DATA_TYPE) */
-/*	#define ECHO_IOC_SET_STRIPE    _IOWR('f', 201, OBD_IOC_DATA_TYPE) */
-/*	#define ECHO_IOC_ENQUEUE       _IOWR('f', 202, OBD_IOC_DATA_TYPE) */
-/*	#define ECHO_IOC_CANCEL        _IOWR('f', 203, OBD_IOC_DATA_TYPE) */
-
-#define OBD_IOC_GET_OBJ_VERSION	_IOR('f', 210, OBD_IOC_DATA_TYPE)
-
-/* <lustre/lustre_user.h> defines ioctl number 218-219 */
-#define OBD_IOC_GET_MNTOPT	     _IOW('f', 220, mntopt_t)
-
-#define OBD_IOC_ECHO_MD		_IOR('f', 221, struct obd_ioctl_data)
-#define OBD_IOC_ECHO_ALLOC_SEQ	 _IOWR('f', 222, struct obd_ioctl_data)
-
-#define OBD_IOC_START_LFSCK	       _IOWR('f', 230, OBD_IOC_DATA_TYPE)
-#define OBD_IOC_STOP_LFSCK	       _IOW('f', 231, OBD_IOC_DATA_TYPE)
-#define OBD_IOC_PAUSE_LFSCK	       _IOW('f', 232, OBD_IOC_DATA_TYPE)
-
-/* XXX _IOWR('f', 250, long) has been defined in
- * libcfs/include/libcfs/libcfs_private.h for debug, don't use it
- */
-
 /* Until such time as we get_info the per-stripe maximum from the OST,
  * we define this to be 2T - 4k, which is the ext3 maxbytes.
  */
diff --git a/drivers/staging/lustre/lustre/include/obd.h b/drivers/staging/lustre/lustre/include/obd.h
index cacd472..0dae273 100644
--- a/drivers/staging/lustre/lustre/include/obd.h
+++ b/drivers/staging/lustre/lustre/include/obd.h
@@ -35,15 +35,6 @@
 
 #include <linux/spinlock.h>
 
-#define IOC_OSC_TYPE	 'h'
-#define IOC_OSC_MIN_NR       20
-#define IOC_OSC_SET_ACTIVE   _IOWR(IOC_OSC_TYPE, 21, struct obd_device *)
-#define IOC_OSC_MAX_NR       50
-
-#define IOC_MDC_TYPE	 'i'
-#define IOC_MDC_MIN_NR       20
-#define IOC_MDC_MAX_NR       50
-
 #include "lustre/lustre_idl.h"
 #include "lustre_lib.h"
 #include "lu_ref.h"
@@ -623,7 +614,6 @@ struct obd_llog_group {
 
 /* corresponds to one of the obd's */
 #define OBD_DEVICE_MAGIC	0XAB5CD6EF
-#define OBD_DEV_BY_DEVNAME      0xffffd0de
 
 struct lvfs_run_ctxt {
 	struct dt_device *dt;
diff --git a/drivers/staging/lustre/lustre/llite/dir.c b/drivers/staging/lustre/lustre/llite/dir.c
index 84bec03..257c9a4 100644
--- a/drivers/staging/lustre/lustre/llite/dir.c
+++ b/drivers/staging/lustre/lustre/llite/dir.c
@@ -46,8 +46,8 @@
 
 #include "../include/obd_support.h"
 #include "../include/obd_class.h"
+#include "../include/lustre/lustre_ioctl.h"
 #include "../include/lustre_lib.h"
-#include "../include/lustre/lustre_idl.h"
 #include "../include/lustre_lite.h"
 #include "../include/lustre_dlm.h"
 #include "../include/lustre_fid.h"
@@ -1543,7 +1543,7 @@ finish_req:
 
 	case LL_IOC_LOV_SWAP_LAYOUTS:
 		return -EPERM;
-	case LL_IOC_OBD_STATFS:
+	case IOC_OBD_STATFS:
 		return ll_obd_statfs(inode, (void __user *)arg);
 	case LL_IOC_LOV_GETSTRIPE:
 	case LL_IOC_MDC_GETINFO:
@@ -1708,9 +1708,6 @@ free_lmm:
 		kvfree(lmm);
 		return rc;
 	}
-	case OBD_IOC_LLOG_CATINFO: {
-		return -EOPNOTSUPP;
-	}
 	case OBD_IOC_QUOTACHECK: {
 		struct obd_quotactl *oqctl;
 		int error = 0;
@@ -1768,7 +1765,7 @@ out_poll:
 		kfree(check);
 		return rc;
 	}
-	case LL_IOC_QUOTACTL: {
+	case OBD_IOC_QUOTACTL: {
 		struct if_quotactl *qctl;
 
 		qctl = kzalloc(sizeof(*qctl), GFP_NOFS);
diff --git a/drivers/staging/lustre/lustre/llite/file.c b/drivers/staging/lustre/lustre/llite/file.c
index 1452a14..343f9b9 100644
--- a/drivers/staging/lustre/lustre/llite/file.c
+++ b/drivers/staging/lustre/lustre/llite/file.c
@@ -44,6 +44,7 @@
 #include <linux/mount.h>
 #include "llite_internal.h"
 #include "../include/lustre/ll_fiemap.h"
+#include "../include/lustre/lustre_ioctl.h"
 
 #include "../include/cl_object.h"
 
diff --git a/drivers/staging/lustre/lustre/llite/llite_lib.c b/drivers/staging/lustre/lustre/llite/llite_lib.c
index e320400..111264e 100644
--- a/drivers/staging/lustre/lustre/llite/llite_lib.c
+++ b/drivers/staging/lustre/lustre/llite/llite_lib.c
@@ -41,6 +41,7 @@
 #include <linux/types.h>
 #include <linux/mm.h>
 
+#include "../include/lustre/lustre_ioctl.h"
 #include "../include/lustre_lite.h"
 #include "../include/lustre_ha.h"
 #include "../include/lustre_dlm.h"
diff --git a/drivers/staging/lustre/lustre/lmv/lmv_obd.c b/drivers/staging/lustre/lustre/lmv/lmv_obd.c
index ff0fbd8..18d7ff8 100644
--- a/drivers/staging/lustre/lustre/lmv/lmv_obd.c
+++ b/drivers/staging/lustre/lustre/lmv/lmv_obd.c
@@ -51,6 +51,7 @@
 #include "../include/cl_object.h"
 #include "../include/lustre_lite.h"
 #include "../include/lustre_fid.h"
+#include "../include/lustre/lustre_ioctl.h"
 #include "../include/lustre_kernelcomm.h"
 #include "lmv_internal.h"
 
diff --git a/drivers/staging/lustre/lustre/lov/lov_obd.c b/drivers/staging/lustre/lustre/lov/lov_obd.c
index 9b92d55..d904f44 100644
--- a/drivers/staging/lustre/lustre/lov/lov_obd.c
+++ b/drivers/staging/lustre/lustre/lov/lov_obd.c
@@ -41,6 +41,7 @@
 #include "../../include/linux/libcfs/libcfs.h"
 
 #include "../include/obd_support.h"
+#include "../include/lustre/lustre_ioctl.h"
 #include "../include/lustre_lib.h"
 #include "../include/lustre_net.h"
 #include "../include/lustre/lustre_idl.h"
diff --git a/drivers/staging/lustre/lustre/mdc/mdc_request.c b/drivers/staging/lustre/lustre/mdc/mdc_request.c
index ce5df23..621ed91 100644
--- a/drivers/staging/lustre/lustre/mdc/mdc_request.c
+++ b/drivers/staging/lustre/lustre/mdc/mdc_request.c
@@ -39,6 +39,7 @@
 # include <linux/utsname.h>
 
 #include "../include/lustre_acl.h"
+#include "../include/lustre/lustre_ioctl.h"
 #include "../include/obd_class.h"
 #include "../include/lustre_lmv.h"
 #include "../include/lustre_fid.h"
diff --git a/drivers/staging/lustre/lustre/obdclass/class_obd.c b/drivers/staging/lustre/lustre/obdclass/class_obd.c
index d9d2a19..6edf53e 100644
--- a/drivers/staging/lustre/lustre/obdclass/class_obd.c
+++ b/drivers/staging/lustre/lustre/obdclass/class_obd.c
@@ -40,6 +40,7 @@
 #include "../include/lprocfs_status.h"
 #include <linux/list.h>
 #include "../include/cl_object.h"
+#include "../include/lustre/lustre_ioctl.h"
 #include "llog_internal.h"
 
 struct obd_device *obd_devs[MAX_OBD_DEVICES];
@@ -287,13 +288,6 @@ int class_handle_ioctl(unsigned int cmd, unsigned long arg)
 		goto out;
 	}
 
-	case OBD_IOC_CLOSE_UUID: {
-		CDEBUG(D_IOCTL, "closing all connections to uuid %s (NOOP)\n",
-		       data->ioc_inlbuf1);
-		err = 0;
-		goto out;
-	}
-
 	case OBD_IOC_GETDEVICE: {
 		int     index = data->ioc_count;
 		char    *status, *str;
diff --git a/drivers/staging/lustre/lustre/obdclass/linux/linux-module.c b/drivers/staging/lustre/lustre/obdclass/linux/linux-module.c
index 33342bf..27a72d8 100644
--- a/drivers/staging/lustre/lustre/obdclass/linux/linux-module.c
+++ b/drivers/staging/lustre/lustre/obdclass/linux/linux-module.c
@@ -65,6 +65,7 @@
 #include "../../include/obd_support.h"
 #include "../../include/obd_class.h"
 #include "../../include/lprocfs_status.h"
+#include "../../include/lustre/lustre_ioctl.h"
 #include "../../include/lustre_ver.h"
 
 /* buffer MUST be at least the size of obd_ioctl_hdr */
diff --git a/drivers/staging/lustre/lustre/obdclass/obd_config.c b/drivers/staging/lustre/lustre/obdclass/obd_config.c
index 0eab123..6d0890f 100644
--- a/drivers/staging/lustre/lustre/obdclass/obd_config.c
+++ b/drivers/staging/lustre/lustre/obdclass/obd_config.c
@@ -37,6 +37,7 @@
 #define DEBUG_SUBSYSTEM S_CLASS
 #include "../include/obd_class.h"
 #include <linux/string.h>
+#include "../include/lustre/lustre_ioctl.h"
 #include "../include/lustre_log.h"
 #include "../include/lprocfs_status.h"
 #include "../include/lustre_param.h"
diff --git a/drivers/staging/lustre/lustre/obdecho/echo_client.c b/drivers/staging/lustre/lustre/obdecho/echo_client.c
index 5b29c4a..2cb487b 100644
--- a/drivers/staging/lustre/lustre/obdecho/echo_client.c
+++ b/drivers/staging/lustre/lustre/obdecho/echo_client.c
@@ -41,6 +41,7 @@
 #include "../include/cl_object.h"
 #include "../include/lustre_fid.h"
 #include "../include/lustre_acl.h"
+#include "../include/lustre/lustre_ioctl.h"
 #include "../include/lustre_net.h"
 
 #include "echo_internal.h"
diff --git a/drivers/staging/lustre/lustre/osc/osc_request.c b/drivers/staging/lustre/lustre/osc/osc_request.c
index a2d948f..d231827 100644
--- a/drivers/staging/lustre/lustre/osc/osc_request.c
+++ b/drivers/staging/lustre/lustre/osc/osc_request.c
@@ -41,6 +41,7 @@
 
 #include "../include/lustre_ha.h"
 #include "../include/lprocfs_status.h"
+#include "../include/lustre/lustre_ioctl.h"
 #include "../include/lustre_debug.h"
 #include "../include/lustre_param.h"
 #include "../include/lustre_fid.h"
-- 
1.7.1

[PATCH 57/58] staging: lustre: llite: add error handler in inode prepare phase

[James Simmons]

From: wang di <di.wang@intel.com>

Add error handler during inode inialization, so inode will
become bad inode if something bad happens during inode prepare
phase, otherwise the striped directory will not get its layout
and being mis-regarded as normal directory.

Signed-off-by: wang di <di.wang@intel.com>
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-4930
Reviewed-on: http://review.whamcloud.com/10170
Reviewed-by: Lai Siyao <lai.siyao@intel.com>
Reviewed-by: Fan Yong <fan.yong@intel.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
Signed-off-by: James Simmons <jsimmons@infradead.org>
---
 .../staging/lustre/lustre/llite/llite_internal.h   |    4 +-
 drivers/staging/lustre/lustre/llite/llite_lib.c    |   66 +++++++++++--------
 drivers/staging/lustre/lustre/llite/namei.c        |   59 ++++++++++--------
 3 files changed, 72 insertions(+), 57 deletions(-)

diff --git a/drivers/staging/lustre/lustre/llite/llite_internal.h b/drivers/staging/lustre/lustre/llite/llite_internal.h
index 120aca3..e101dd8 100644
--- a/drivers/staging/lustre/lustre/llite/llite_internal.h
+++ b/drivers/staging/lustre/lustre/llite/llite_internal.h
@@ -766,8 +766,8 @@ int ll_setattr(struct dentry *de, struct iattr *attr);
 int ll_statfs(struct dentry *de, struct kstatfs *sfs);
 int ll_statfs_internal(struct super_block *sb, struct obd_statfs *osfs,
 		       __u64 max_age, __u32 flags);
-void ll_update_inode(struct inode *inode, struct lustre_md *md);
-void ll_read_inode2(struct inode *inode, void *opaque);
+int ll_update_inode(struct inode *inode, struct lustre_md *md);
+int ll_read_inode2(struct inode *inode, void *opaque);
 void ll_delete_inode(struct inode *inode);
 int ll_iocontrol(struct inode *inode, struct file *file,
 		 unsigned int cmd, unsigned long arg);
diff --git a/drivers/staging/lustre/lustre/llite/llite_lib.c b/drivers/staging/lustre/lustre/llite/llite_lib.c
index 111264e..ea79ca3 100644
--- a/drivers/staging/lustre/lustre/llite/llite_lib.c
+++ b/drivers/staging/lustre/lustre/llite/llite_lib.c
@@ -464,7 +464,7 @@ static int client_common_fill_super(struct super_block *sb, char *md, char *dt,
 	md_free_lustre_md(sbi->ll_md_exp, &lmd);
 	ptlrpc_req_finished(request);
 
-	if (!(root)) {
+	if (IS_ERR(root)) {
 		if (lmd.lsm)
 			obd_free_memmd(sbi->ll_dt_exp, &lmd.lsm);
 #ifdef CONFIG_FS_POSIX_ACL
@@ -1109,11 +1109,11 @@ static inline int lli_lsm_md_eq(const struct lmv_stripe_md *lsm_md1,
 		       lsm_md2->lsm_md_pool_name);
 }
 
-static void ll_update_lsm_md(struct inode *inode, struct lustre_md *md)
+static int ll_update_lsm_md(struct inode *inode, struct lustre_md *md)
 {
 	struct ll_inode_info *lli = ll_i2info(inode);
 	struct lmv_stripe_md *lsm = md->lmv;
-	int idx;
+	int idx, rc;
 
 	LASSERT(S_ISDIR(inode->i_mode));
 	CDEBUG(D_INODE, "update lsm %p of "DFID"\n", lli->lli_lsm_md,
@@ -1122,7 +1122,7 @@ static void ll_update_lsm_md(struct inode *inode, struct lustre_md *md)
 	/* no striped information from request. */
 	if (!lsm) {
 		if (!lli->lli_lsm_md) {
-			return;
+			return 0;
 		} else if (lli->lli_lsm_md->lsm_md_magic == LMV_MAGIC_MIGRATE) {
 			/*
 			 * migration is done, the temporay MIGRATE layout has
@@ -1132,27 +1132,22 @@ static void ll_update_lsm_md(struct inode *inode, struct lustre_md *md)
 			       PFID(ll_inode2fid(inode)));
 			lmv_free_memmd(lli->lli_lsm_md);
 			lli->lli_lsm_md = NULL;
-			return;
+			return 0;
 		} else {
 			/*
 			 * The lustre_md from req does not include stripeEA,
 			 * see ll_md_setattr
 			 */
-			return;
+			return 0;
 		}
 	}
 
 	/* set the directory layout */
 	if (!lli->lli_lsm_md) {
-		int rc;
-
 		rc = ll_init_lsm_md(inode, md);
-		if (rc) {
-			CERROR("%s: init "DFID" failed: rc = %d\n",
-			       ll_get_fsname(inode->i_sb, NULL, 0),
-			       PFID(&lli->lli_fid), rc);
-			return;
-		}
+		if (rc)
+			return rc;
+
 		lli->lli_lsm_md = lsm;
 		/*
 		 * set lsm_md to NULL, so the following free lustre_md
@@ -1161,7 +1156,7 @@ static void ll_update_lsm_md(struct inode *inode, struct lustre_md *md)
 		md->lmv = NULL;
 		CDEBUG(D_INODE, "Set lsm %p magic %x to "DFID"\n", lsm,
 		       lsm->lsm_md_magic, PFID(ll_inode2fid(inode)));
-		return;
+		return 0;
 	}
 
 	/* Compare the old and new stripe information */
@@ -1185,7 +1180,7 @@ static void ll_update_lsm_md(struct inode *inode, struct lustre_md *md)
 		       lli->lli_lsm_md->lsm_md_layout_version,
 		       lsm->lsm_md_pool_name,
 		       lli->lli_lsm_md->lsm_md_pool_name);
-		return;
+		return -EIO;
 	}
 
 	for (idx = 0; idx < lli->lli_lsm_md->lsm_md_stripe_count; idx++) {
@@ -1195,12 +1190,13 @@ static void ll_update_lsm_md(struct inode *inode, struct lustre_md *md)
 			       ll_get_fsname(inode->i_sb, NULL, 0), idx,
 			       PFID(&lli->lli_lsm_md->lsm_md_oinfo[idx].lmo_fid),
 			       PFID(&lsm->lsm_md_oinfo[idx].lmo_fid));
-			return;
+			return -EIO;
 		}
 	}
 
-	md_update_lsm_md(ll_i2mdexp(inode), ll_i2info(inode)->lli_lsm_md,
-			 md->body, ll_md_blocking_ast);
+	rc = md_update_lsm_md(ll_i2mdexp(inode), ll_i2info(inode)->lli_lsm_md,
+			      md->body, ll_md_blocking_ast);
+	return rc;
 }
 
 void ll_clear_inode(struct inode *inode)
@@ -1252,7 +1248,7 @@ void ll_clear_inode(struct inode *inode)
 
 	if (S_ISDIR(inode->i_mode))
 		ll_dir_clear_lsm_md(inode);
-	else
+	if (S_ISREG(inode->i_mode) && !is_bad_inode(inode))
 		LASSERT(list_empty(&lli->lli_agl_list));
 
 	/*
@@ -1320,7 +1316,7 @@ static int ll_md_setattr(struct dentry *dentry, struct md_op_data *op_data,
 	op_data->op_handle = md.body->handle;
 	op_data->op_ioepoch = md.body->ioepoch;
 
-	ll_update_inode(inode, &md);
+	rc = ll_update_inode(inode, &md);
 	ptlrpc_req_finished(request);
 
 	return rc;
@@ -1679,7 +1675,7 @@ void ll_inode_size_unlock(struct inode *inode)
 	mutex_unlock(&lli->lli_size_mutex);
 }
 
-void ll_update_inode(struct inode *inode, struct lustre_md *md)
+int ll_update_inode(struct inode *inode, struct lustre_md *md)
 {
 	struct ll_inode_info *lli = ll_i2info(inode);
 	struct mdt_body *body = md->body;
@@ -1697,8 +1693,13 @@ void ll_update_inode(struct inode *inode, struct lustre_md *md)
 			lli->lli_maxbytes = MAX_LFS_FILESIZE;
 	}
 
-	if (S_ISDIR(inode->i_mode))
-		ll_update_lsm_md(inode, md);
+	if (S_ISDIR(inode->i_mode)) {
+		int rc;
+
+		rc = ll_update_lsm_md(inode, md);
+		if (rc)
+			return rc;
+	}
 
 #ifdef CONFIG_FS_POSIX_ACL
 	if (body->valid & OBD_MD_FLACL) {
@@ -1819,12 +1820,15 @@ void ll_update_inode(struct inode *inode, struct lustre_md *md)
 		if (body->t_state & MS_RESTORE)
 			lli->lli_flags |= LLIF_FILE_RESTORING;
 	}
+
+	return 0;
 }
 
-void ll_read_inode2(struct inode *inode, void *opaque)
+int ll_read_inode2(struct inode *inode, void *opaque)
 {
 	struct lustre_md *md = opaque;
 	struct ll_inode_info *lli = ll_i2info(inode);
+	int rc;
 
 	CDEBUG(D_VFSTRACE, "VFS Op:inode="DFID"(%p)\n",
 	       PFID(&lli->lli_fid), inode);
@@ -1840,7 +1844,9 @@ void ll_read_inode2(struct inode *inode, void *opaque)
 	LTIME_S(inode->i_atime) = 0;
 	LTIME_S(inode->i_ctime) = 0;
 	inode->i_rdev = 0;
-	ll_update_inode(inode, md);
+	rc = ll_update_inode(inode, md);
+	if (rc)
+		return rc;
 
 	/* OIDEBUG(inode); */
 
@@ -1861,6 +1867,8 @@ void ll_read_inode2(struct inode *inode, void *opaque)
 		init_special_inode(inode, inode->i_mode,
 				   inode->i_rdev);
 	}
+
+	return 0;
 }
 
 void ll_delete_inode(struct inode *inode)
@@ -2127,7 +2135,9 @@ int ll_prep_inode(struct inode **inode, struct ptlrpc_request *req,
 		goto cleanup;
 
 	if (*inode) {
-		ll_update_inode(*inode, &md);
+		rc = ll_update_inode(*inode, &md);
+		if (rc)
+			goto out;
 	} else {
 		LASSERT(sb);
 
@@ -2146,7 +2156,7 @@ int ll_prep_inode(struct inode **inode, struct ptlrpc_request *req,
 		*inode = ll_iget(sb, cl_fid_build_ino(&md.body->fid1,
 					     sbi->ll_flags & LL_SBI_32BIT_API),
 				 &md);
-		if (!*inode) {
+		if (IS_ERR(*inode)) {
 #ifdef CONFIG_FS_POSIX_ACL
 			if (md.posix_acl) {
 				posix_acl_release(md.posix_acl);
diff --git a/drivers/staging/lustre/lustre/llite/namei.c b/drivers/staging/lustre/lustre/llite/namei.c
index 41591dd..5dcedb0 100644
--- a/drivers/staging/lustre/lustre/llite/namei.c
+++ b/drivers/staging/lustre/lustre/llite/namei.c
@@ -96,41 +96,46 @@ static int ll_set_inode(struct inode *inode, void *opaque)
 	return 0;
 }
 
-/*
- * Get an inode by inode number (already instantiated by the intent lookup).
- * Returns inode or NULL
+/**
+ * Get an inode by inode number(@hash), which is already instantiated by
+ * the intent lookup).
  */
 struct inode *ll_iget(struct super_block *sb, ino_t hash,
 		      struct lustre_md *md)
 {
 	struct inode	 *inode;
+	int rc = 0;
 
 	LASSERT(hash != 0);
 	inode = iget5_locked(sb, hash, ll_test_inode, ll_set_inode, md);
-
-	if (inode) {
-		if (inode->i_state & I_NEW) {
-			int rc = 0;
-
-			ll_read_inode2(inode, md);
-			if (S_ISREG(inode->i_mode) &&
-			    !ll_i2info(inode)->lli_clob) {
-				CDEBUG(D_INODE,
-				       "%s: apply lsm %p to inode " DFID ".\n",
-				       ll_get_fsname(sb, NULL, 0), md->lsm,
-				       PFID(ll_inode2fid(inode)));
-				rc = cl_file_inode_init(inode, md);
-			}
-			if (rc != 0) {
-				iget_failed(inode);
-				inode = NULL;
-			} else {
-				unlock_new_inode(inode);
-			}
-		} else if (!(inode->i_state & (I_FREEING | I_CLEAR))) {
-			ll_update_inode(inode, md);
-			CDEBUG(D_VFSTRACE, "got inode: "DFID"(%p)\n",
-			       PFID(&md->body->fid1), inode);
+	if (!inode)
+		return ERR_PTR(-ENOMEM);
+
+	if (inode->i_state & I_NEW) {
+		rc = ll_read_inode2(inode, md);
+		if (!rc && S_ISREG(inode->i_mode) &&
+		    !ll_i2info(inode)->lli_clob) {
+			CDEBUG(D_INODE, "%s: apply lsm %p to inode "DFID"\n",
+			       ll_get_fsname(sb, NULL, 0), md->lsm,
+			       PFID(ll_inode2fid(inode)));
+			rc = cl_file_inode_init(inode, md);
+		}
+		if (rc) {
+			make_bad_inode(inode);
+			unlock_new_inode(inode);
+			iput(inode);
+			inode = ERR_PTR(rc);
+		} else {
+			unlock_new_inode(inode);
+		}
+	} else if (!(inode->i_state & (I_FREEING | I_CLEAR))) {
+		rc = ll_update_inode(inode, md);
+		CDEBUG(D_VFSTRACE, "got inode: "DFID"(%p): rc = %d\n",
+		       PFID(&md->body->fid1), inode, rc);
+		if (rc) {
+			make_bad_inode(inode);
+			iput(inode);
+			inode = ERR_PTR(rc);
 		}
 	}
 	return inode;
-- 
1.7.1

[PATCH 58/58] staging: lustre: ptlrpc: Early replies need to honor at_max

[James Simmons]

From: Chris Horn <hornc@cray.com>

When determining whether an early reply can be sent the server will
calculate the new deadline based on an offset from the request
arrival time. However, when actually setting the new deadline
the server offsets the current time. This can result in deadlines
being extended more than at_max seconds past the request arrival
time. Instead, the server should offset the arrival time when updating
its request timeout.

When a client receives an early reply it doesn't know the server side
arrival time so we use the original sent time as an approximation.

Signed-off-by: Chris Horn <hornc@cray.com>
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-4578
Reviewed-on: http://review.whamcloud.com/9100
Reviewed-by: James Simmons <uja.ornl@gmail.com>
Reviewed-by: Christopher J. Morrone <chris.morrone.llnl@gmail.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
Signed-off-by: James Simmons <jsimmons@infradead.org>
---
 drivers/staging/lustre/lustre/ptlrpc/client.c  |    8 +++++---
 drivers/staging/lustre/lustre/ptlrpc/import.c  |   11 +++++++----
 drivers/staging/lustre/lustre/ptlrpc/service.c |   18 +++++++++++++-----
 3 files changed, 25 insertions(+), 12 deletions(-)

diff --git a/drivers/staging/lustre/lustre/ptlrpc/client.c b/drivers/staging/lustre/lustre/ptlrpc/client.c
index d4463d7..ddb08ea 100644
--- a/drivers/staging/lustre/lustre/ptlrpc/client.c
+++ b/drivers/staging/lustre/lustre/ptlrpc/client.c
@@ -385,10 +385,12 @@ static int ptlrpc_at_recv_early_reply(struct ptlrpc_request *req)
 	spin_lock(&req->rq_lock);
 	olddl = req->rq_deadline;
 	/*
-	 * server assumes it now has rq_timeout from when it sent the
-	 * early reply, so client should give it at least that long.
+	 * server assumes it now has rq_timeout from when the request
+	 * arrived, so the client should give it at least that long.
+	 * since we don't know the arrival time we'll use the original
+	 * sent time
 	 */
-	req->rq_deadline = ktime_get_real_seconds() + req->rq_timeout +
+	req->rq_deadline = req->rq_sent + req->rq_timeout +
 			   ptlrpc_at_get_net_latency(req);
 
 	DEBUG_REQ(D_ADAPTTO, req,
diff --git a/drivers/staging/lustre/lustre/ptlrpc/import.c b/drivers/staging/lustre/lustre/ptlrpc/import.c
index 3292e6e..af8ffbc 100644
--- a/drivers/staging/lustre/lustre/ptlrpc/import.c
+++ b/drivers/staging/lustre/lustre/ptlrpc/import.c
@@ -1497,10 +1497,13 @@ EXPORT_SYMBOL(ptlrpc_disconnect_import);
 /* Adaptive Timeout utils */
 extern unsigned int at_min, at_max, at_history;
 
-/* Bin into timeslices using AT_BINS bins.
- * This gives us a max of the last binlimit*AT_BINS secs without the storage,
- * but still smoothing out a return to normalcy from a slow response.
- * (E.g. remember the maximum latency in each minute of the last 4 minutes.)
+/*
+ *Update at_current with the specified value (bounded by at_min and at_max),
+ * as well as the AT history "bins".
+ *  - Bin into timeslices using AT_BINS bins.
+ *  - This gives us a max of the last at_history seconds without the storage,
+ *    but still smoothing out a return to normalcy from a slow response.
+ *  - (E.g. remember the maximum latency in each minute of the last 4 minutes.)
  */
 int at_measured(struct adaptive_timeout *at, unsigned int val)
 {
diff --git a/drivers/staging/lustre/lustre/ptlrpc/service.c b/drivers/staging/lustre/lustre/ptlrpc/service.c
index 4788c49..30d8b72 100644
--- a/drivers/staging/lustre/lustre/ptlrpc/service.c
+++ b/drivers/staging/lustre/lustre/ptlrpc/service.c
@@ -1005,13 +1005,16 @@ ptlrpc_at_remove_timed(struct ptlrpc_request *req)
 	array->paa_count--;
 }
 
+/*
+ * Attempt to extend the request deadline by sending an early reply to the
+ * client.
+ */
 static int ptlrpc_at_send_early_reply(struct ptlrpc_request *req)
 {
 	struct ptlrpc_service_part *svcpt = req->rq_rqbd->rqbd_svcpt;
 	struct ptlrpc_request *reqcopy;
 	struct lustre_msg *reqmsg;
 	long olddl = req->rq_deadline - ktime_get_real_seconds();
-	time64_t newdl;
 	int rc;
 
 	/* deadline is when the client expects us to reply, margin is the
@@ -1039,8 +1042,13 @@ static int ptlrpc_at_send_early_reply(struct ptlrpc_request *req)
 		return -ENOSYS;
 	}
 
-	/* Fake our processing time into the future to ask the clients
-	 * for some extra amount of time
+	/*
+	 * We want to extend the request deadline by at_extra seconds,
+	 * so we set our service estimate to reflect how much time has
+	 * passed since this request arrived plus an additional
+	 * at_extra seconds. The client will calculate the new deadline
+	 * based on this service estimate (plus some additional time to
+	 * account for network latency). See ptlrpc_at_recv_early_reply
 	 */
 	at_measured(&svcpt->scp_at_estimate, at_extra +
 		    ktime_get_real_seconds() - req->rq_arrival_time.tv_sec);
@@ -1056,7 +1064,6 @@ static int ptlrpc_at_send_early_reply(struct ptlrpc_request *req)
 			  ktime_get_real_seconds());
 		return -ETIMEDOUT;
 	}
-	newdl = ktime_get_real_seconds() + at_get(&svcpt->scp_at_estimate);
 
 	reqcopy = ptlrpc_request_cache_alloc(GFP_NOFS);
 	if (!reqcopy)
@@ -1110,7 +1117,8 @@ static int ptlrpc_at_send_early_reply(struct ptlrpc_request *req)
 
 	if (!rc) {
 		/* Adjust our own deadline to what we told the client */
-		req->rq_deadline = newdl;
+		req->rq_deadline = req->rq_arrival_time.tv_sec +
+				   at_get(&svcpt->scp_at_estimate);
 		req->rq_early_count++; /* number sent, server side */
 	} else {
 		DEBUG_REQ(D_ERROR, req, "Early reply send failed %d", rc);
-- 
1.7.1

Re: [PATCH 30/58] staging: lustre: create striped directory

[kbuild test robot]

[-- Attachment #1: Type: text/plain, Size: 814 bytes --]

Hi,

[auto build test ERROR on staging/staging-testing]
[also build test ERROR on next-20160722]
[cannot apply to v4.7-rc7]
[if your patch is applied to the wrong git tree, please drop us a note to help improve the system]

url:    https://github.com/0day-ci/linux/commits/James-Simmons/staging-lustre-bug-fixes-from-lustre-2-5-56-58/20160722-145652
config: i386-allyesconfig (attached as .config)
compiler: gcc-6 (Debian 6.1.1-9) 6.1.1 20160705
reproduce:
        # save the attached .config to linux build tree
        make ARCH=i386 

All errors (new ones prefixed by >>):

>> ERROR: "__umoddi3" [drivers/staging/lustre/lustre/lmv/lmv.ko] undefined!

---
0-DAY kernel test infrastructure                Open Source Technology Center
https://lists.01.org/pipermail/kbuild-all                   Intel Corporation

[-- Attachment #2: .config.gz --]
[-- Type: application/octet-stream, Size: 54414 bytes --]

[PATCH v2 30/58] staging: lustre: create striped directory

[James Simmons]

[-- Warning: decoded text below may be mangled, UTF-8 assumed --]
[-- Attachment #1: Type: text/plain, Size: 49177 bytes --]

From: wang di <di.wang@intel.com>

1. client send create request to the master MDT, which
  will allocate FIDs and create slaves. for all of slaves.

2. Client needs to revalidate slaves during intent getattr
   and open request.

3. lmv_stripe_md will include attributes(size, nlink etc)
   from all of stripe, which will be protected by UPDATE lock.
   client needs to merge these attributes when update inode.

4. send create request to the MDT where the file is located,
   which can help creating master stripe of striped directory.

Changelog

v1) Original submitted patch

v2) fixed lmv_hash_fnv1a function to use do_div64 to fix
    __umoddi3 undefined bug on 32 bit platforms.

Signed-off-by: wang di <di.wang@intel.com>
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-3529
Reviewed-on: http://review.whamcloud.com/7196
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>
Signed-off-by: James Simmons <jsimmons@infradead.org>
---
 drivers/staging/lustre/lustre/include/cl_object.h  |    3 +
 .../lustre/lustre/include/lustre/lustre_idl.h      |   40 +++-
 .../lustre/lustre/include/lustre/lustre_user.h     |   16 +-
 drivers/staging/lustre/lustre/include/lustre_lib.h |    2 +
 drivers/staging/lustre/lustre/include/lustre_lmv.h |   59 +++++
 drivers/staging/lustre/lustre/include/obd.h        |   16 +-
 drivers/staging/lustre/lustre/include/obd_class.h  |   19 ++
 drivers/staging/lustre/lustre/llite/dir.c          |   26 ++-
 drivers/staging/lustre/lustre/llite/file.c         |   40 +++-
 .../staging/lustre/lustre/llite/llite_internal.h   |   12 +-
 drivers/staging/lustre/lustre/llite/llite_lib.c    |  193 +++++++++++++++-
 drivers/staging/lustre/lustre/llite/llite_nfs.c    |    7 +-
 drivers/staging/lustre/lustre/llite/namei.c        |   42 +++-
 drivers/staging/lustre/lustre/lmv/lmv_intent.c     |  244 +++++++++++++++++---
 drivers/staging/lustre/lustre/lmv/lmv_internal.h   |   32 +++
 drivers/staging/lustre/lustre/lmv/lmv_obd.c        |  221 +++++++++++++++---
 drivers/staging/lustre/lustre/mdc/mdc_locks.c      |    3 +
 .../staging/lustre/lustre/ptlrpc/pack_generic.c    |   11 +
 18 files changed, 880 insertions(+), 106 deletions(-)

diff --git a/drivers/staging/lustre/lustre/include/cl_object.h b/drivers/staging/lustre/lustre/include/cl_object.h
index 3cd4a25..0fa71a5 100644
--- a/drivers/staging/lustre/lustre/include/cl_object.h
+++ b/drivers/staging/lustre/lustre/include/cl_object.h
@@ -191,6 +191,9 @@ struct cl_attr {
 	 * Group identifier for quota purposes.
 	 */
 	gid_t  cat_gid;
+
+	/* nlink of the directory */
+	__u64  cat_nlink;
 };
 
 /**
diff --git a/drivers/staging/lustre/lustre/include/lustre/lustre_idl.h b/drivers/staging/lustre/lustre/include/lustre/lustre_idl.h
index 0ad6605..a612080 100644
--- a/drivers/staging/lustre/lustre/include/lustre/lustre_idl.h
+++ b/drivers/staging/lustre/lustre/include/lustre/lustre_idl.h
@@ -1610,6 +1610,7 @@ static inline void lmm_oi_cpu_to_le(struct ost_id *dst_oi,
 #define XATTR_NAME_LOV	  "trusted.lov"
 #define XATTR_NAME_LMA	  "trusted.lma"
 #define XATTR_NAME_LMV	  "trusted.lmv"
+#define XATTR_NAME_DEFAULT_LMV	"trusted.dmv"
 #define XATTR_NAME_LINK	 "trusted.link"
 #define XATTR_NAME_FID	  "trusted.fid"
 #define XATTR_NAME_VERSION      "trusted.version"
@@ -2472,7 +2473,7 @@ struct lmv_desc {
 	__u32 ld_tgt_count;		/* how many MDS's */
 	__u32 ld_active_tgt_count;	 /* how many active */
 	__u32 ld_default_stripe_count;     /* how many objects are used */
-	__u32 ld_pattern;		  /* default MEA_MAGIC_* */
+	__u32 ld_pattern;		  /* default hash pattern */
 	__u64 ld_default_hash_size;
 	__u64 ld_padding_1;		/* also fix lustre_swab_lmv_desc */
 	__u32 ld_padding_2;		/* also fix lustre_swab_lmv_desc */
@@ -2486,6 +2487,43 @@ struct lmv_desc {
 #define LMV_MAGIC_V1	0x0CD10CD0	/* normal stripe lmv magic */
 #define LMV_USER_MAGIC	0x0CD20CD0	/* default lmv magic*/
 #define LMV_MAGIC	LMV_MAGIC_V1
+
+enum lmv_hash_type {
+	LMV_HASH_TYPE_ALL_CHARS = 1,
+	LMV_HASH_TYPE_FNV_1A_64 = 2,
+};
+
+#define LMV_HASH_NAME_ALL_CHARS		"all_char"
+#define LMV_HASH_NAME_FNV_1A_64		"fnv_1a_64"
+
+/**
+ * The FNV-1a hash algorithm is as follows:
+ *     hash = FNV_offset_basis
+ *     for each octet_of_data to be hashed
+ *             hash = hash XOR octet_of_data
+ *             hash = hash × FNV_prime
+ *     return hash
+ * http://en.wikipedia.org/wiki/Fowler–Noll–Vo_hash_function#FNV-1a_hash
+ *
+ * http://www.isthe.com/chongo/tech/comp/fnv/index.html#FNV-reference-source
+ * FNV_prime is 2^40 + 2^8 + 0xb3 = 0x100000001b3ULL
+ **/
+#define LUSTRE_FNV_1A_64_PRIME		0x100000001b3ULL
+#define LUSTRE_FNV_1A_64_OFFSET_BIAS	0xcbf29ce484222325ULL
+static inline __u64 lustre_hash_fnv_1a_64(const void *buf, size_t size)
+{
+	__u64 hash = LUSTRE_FNV_1A_64_OFFSET_BIAS;
+	const unsigned char *p = buf;
+	size_t i;
+
+	for (i = 0; i < size; i++) {
+		hash ^= p[i];
+		hash *= LUSTRE_FNV_1A_64_PRIME;
+	}
+
+	return hash;
+}
+
 struct lmv_mds_md_v1 {
 	__u32 lmv_magic;
 	__u32 lmv_stripe_count;		/* stripe count */
diff --git a/drivers/staging/lustre/lustre/include/lustre/lustre_user.h b/drivers/staging/lustre/lustre/include/lustre/lustre_user.h
index ef6f38f..d496d0e 100644
--- a/drivers/staging/lustre/lustre/include/lustre/lustre_user.h
+++ b/drivers/staging/lustre/lustre/include/lustre/lustre_user.h
@@ -374,19 +374,17 @@ struct lov_user_mds_data_v3 {
 } __packed;
 #endif
 
-/* keep this to be the same size as lov_user_ost_data_v1 */
 struct lmv_user_mds_data {
 	struct lu_fid	lum_fid;
 	__u32		lum_padding;
 	__u32		lum_mds;
 };
 
-/* lum_type */
-enum {
-	LMV_STRIPE_TYPE = 0,
-	LMV_DEFAULT_TYPE = 1,
-};
-
+/*
+ * Got this according to how get LOV_MAX_STRIPE_COUNT, see above,
+ * (max buffer size - lmv+rpc header) / sizeof(struct lmv_user_mds_data)
+ */
+#define LMV_MAX_STRIPE_COUNT 2000  /* ((12 * 4096 - 256) / 24) */
 #define lmv_user_md lmv_user_md_v1
 struct lmv_user_md_v1 {
 	__u32	lum_magic;	 /* must be the first field */
@@ -399,7 +397,7 @@ struct lmv_user_md_v1 {
 	__u32	lum_padding3;
 	char	lum_pool_name[LOV_MAXPOOLNAME];
 	struct	lmv_user_mds_data  lum_objects[0];
-};
+} __packed;
 
 static inline int lmv_user_md_size(int stripes, int lmm_magic)
 {
@@ -407,6 +405,8 @@ static inline int lmv_user_md_size(int stripes, int lmm_magic)
 		      stripes * sizeof(struct lmv_user_mds_data);
 }
 
+void lustre_swab_lmv_user_md(struct lmv_user_md *lum);
+
 struct ll_recreate_obj {
 	__u64 lrc_id;
 	__u32 lrc_ost_idx;
diff --git a/drivers/staging/lustre/lustre/include/lustre_lib.h b/drivers/staging/lustre/lustre/include/lustre_lib.h
index 06958f2..def0193 100644
--- a/drivers/staging/lustre/lustre/include/lustre_lib.h
+++ b/drivers/staging/lustre/lustre/include/lustre_lib.h
@@ -391,6 +391,8 @@ static inline void obd_ioctl_freedata(char *buf, int len)
 #define LOVEA_DELETE_VALUES(size, count, offset) (size == 0 && count == 0 && \
 						 offset == (typeof(offset))(-1))
 
+#define LMVEA_DELETE_VALUES(count, offset) ((count) == 0 && \
+					    (offset) == (typeof(offset))(-1))
 /* #define POISON_BULK 0 */
 
 /*
diff --git a/drivers/staging/lustre/lustre/include/lustre_lmv.h b/drivers/staging/lustre/lustre/include/lustre_lmv.h
index 784d67b..4036fce 100644
--- a/drivers/staging/lustre/lustre/include/lustre_lmv.h
+++ b/drivers/staging/lustre/lustre/include/lustre_lmv.h
@@ -66,4 +66,63 @@ static inline void lmv_free_memmd(struct lmv_stripe_md *lsm)
 {
 	lmv_unpack_md(NULL, &lsm, NULL, 0);
 }
+
+static inline void lmv1_cpu_to_le(struct lmv_mds_md_v1 *lmv_dst,
+				  const struct lmv_mds_md_v1 *lmv_src)
+{
+	int i;
+
+	lmv_dst->lmv_magic = cpu_to_le32(lmv_src->lmv_magic);
+	lmv_dst->lmv_stripe_count = cpu_to_le32(lmv_src->lmv_stripe_count);
+	lmv_dst->lmv_master_mdt_index =
+		cpu_to_le32(lmv_src->lmv_master_mdt_index);
+	lmv_dst->lmv_hash_type = cpu_to_le32(lmv_src->lmv_hash_type);
+	lmv_dst->lmv_layout_version = cpu_to_le32(lmv_src->lmv_layout_version);
+
+	for (i = 0; i < lmv_src->lmv_stripe_count; i++)
+		fid_cpu_to_le(&lmv_dst->lmv_stripe_fids[i],
+			      &lmv_src->lmv_stripe_fids[i]);
+}
+
+static inline void lmv1_le_to_cpu(struct lmv_mds_md_v1 *lmv_dst,
+				  const struct lmv_mds_md_v1 *lmv_src)
+{
+	int i;
+
+	lmv_dst->lmv_magic = le32_to_cpu(lmv_src->lmv_magic);
+	lmv_dst->lmv_stripe_count = le32_to_cpu(lmv_src->lmv_stripe_count);
+	lmv_dst->lmv_master_mdt_index =
+		le32_to_cpu(lmv_src->lmv_master_mdt_index);
+	lmv_dst->lmv_hash_type = le32_to_cpu(lmv_src->lmv_hash_type);
+	lmv_dst->lmv_layout_version = le32_to_cpu(lmv_src->lmv_layout_version);
+
+	for (i = 0; i < lmv_src->lmv_stripe_count; i++)
+		fid_le_to_cpu(&lmv_dst->lmv_stripe_fids[i],
+			      &lmv_src->lmv_stripe_fids[i]);
+}
+
+static inline void lmv_cpu_to_le(union lmv_mds_md *lmv_dst,
+				 const union lmv_mds_md *lmv_src)
+{
+	switch (lmv_src->lmv_magic) {
+	case LMV_MAGIC_V1:
+		lmv1_cpu_to_le(&lmv_dst->lmv_md_v1, &lmv_src->lmv_md_v1);
+		break;
+	default:
+		break;
+	}
+}
+
+static inline void lmv_le_to_cpu(union lmv_mds_md *lmv_dst,
+				 const union lmv_mds_md *lmv_src)
+{
+	switch (le32_to_cpu(lmv_src->lmv_magic)) {
+	case LMV_MAGIC_V1:
+		lmv1_le_to_cpu(&lmv_dst->lmv_md_v1, &lmv_src->lmv_md_v1);
+		break;
+	default:
+		break;
+	}
+}
+
 #endif
diff --git a/drivers/staging/lustre/lustre/include/obd.h b/drivers/staging/lustre/lustre/include/obd.h
index 17b8d22..a9f4e13 100644
--- a/drivers/staging/lustre/lustre/include/obd.h
+++ b/drivers/staging/lustre/lustre/include/obd.h
@@ -1022,14 +1022,6 @@ enum {
 };
 
 /* lmv structures */
-#define MEA_MAGIC_LAST_CHAR      0xb2221ca1
-#define MEA_MAGIC_ALL_CHARS      0xb222a11c
-#define MEA_MAGIC_HASH_SEGMENT   0xb222a11b
-
-#define MAX_HASH_SIZE_32	 0x7fffffffUL
-#define MAX_HASH_SIZE	    0x7fffffffffffffffULL
-#define MAX_HASH_HIGHEST_BIT     0x1000000000000000ULL
-
 struct lustre_md {
 	struct mdt_body	 *body;
 	struct lov_stripe_md    *lsm;
@@ -1049,6 +1041,7 @@ struct md_open_data {
 };
 
 struct lookup_intent;
+struct cl_attr;
 
 struct md_ops {
 	int (*getstatus)(struct obd_export *, struct lu_fid *);
@@ -1109,6 +1102,13 @@ struct md_ops {
 
 	int (*free_lustre_md)(struct obd_export *, struct lustre_md *);
 
+	int (*merge_attr)(struct obd_export *,
+			  const struct lmv_stripe_md *lsm,
+			  struct cl_attr *attr);
+
+	int (*update_lsm_md)(struct obd_export *, struct lmv_stripe_md *lsm,
+			     struct mdt_body *, ldlm_blocking_callback);
+
 	int (*set_open_replay_data)(struct obd_export *,
 				    struct obd_client_handle *,
 				    struct lookup_intent *);
diff --git a/drivers/staging/lustre/lustre/include/obd_class.h b/drivers/staging/lustre/lustre/include/obd_class.h
index 6482a93..2f111a8 100644
--- a/drivers/staging/lustre/lustre/include/obd_class.h
+++ b/drivers/staging/lustre/lustre/include/obd_class.h
@@ -1559,6 +1559,25 @@ static inline int md_free_lustre_md(struct obd_export *exp,
 	return MDP(exp->exp_obd, free_lustre_md)(exp, md);
 }
 
+static inline int md_update_lsm_md(struct obd_export *exp,
+				   struct lmv_stripe_md *lsm,
+				   struct mdt_body *body,
+				   ldlm_blocking_callback cb)
+{
+	EXP_CHECK_MD_OP(exp, update_lsm_md);
+	EXP_MD_COUNTER_INCREMENT(exp, update_lsm_md);
+	return MDP(exp->exp_obd, update_lsm_md)(exp, lsm, body, cb);
+}
+
+static inline int md_merge_attr(struct obd_export *exp,
+				const struct lmv_stripe_md *lsm,
+				struct cl_attr *attr)
+{
+	EXP_CHECK_MD_OP(exp, merge_attr);
+	EXP_MD_COUNTER_INCREMENT(exp, merge_attr);
+	return MDP(exp->exp_obd, merge_attr)(exp, lsm, attr);
+}
+
 static inline int md_setxattr(struct obd_export *exp, const struct lu_fid *fid,
 			      u64 valid, const char *name,
 			      const char *input, int input_size,
diff --git a/drivers/staging/lustre/lustre/llite/dir.c b/drivers/staging/lustre/lustre/llite/dir.c
index a72b486..a0560b6 100644
--- a/drivers/staging/lustre/lustre/llite/dir.c
+++ b/drivers/staging/lustre/lustre/llite/dir.c
@@ -668,7 +668,7 @@ static int ll_send_mgc_param(struct obd_export *mgc, char *string)
 }
 
 static int ll_dir_setdirstripe(struct inode *dir, struct lmv_user_md *lump,
-			       char *filename)
+			       const char *filename)
 {
 	struct ptlrpc_request *request = NULL;
 	struct md_op_data *op_data;
@@ -676,6 +676,26 @@ static int ll_dir_setdirstripe(struct inode *dir, struct lmv_user_md *lump,
 	int mode;
 	int err;
 
+	if (unlikely(lump->lum_magic != LMV_USER_MAGIC))
+		return -EINVAL;
+
+	if (lump->lum_stripe_offset == (__u32)-1) {
+		int mdtidx;
+
+		mdtidx = ll_get_mdt_idx(dir);
+		if (mdtidx < 0)
+			return mdtidx;
+
+		lump->lum_stripe_offset = mdtidx;
+	}
+
+	CDEBUG(D_VFSTRACE, "VFS Op:inode="DFID"(%p) name %s stripe_offset %d, stripe_count: %u\n",
+	       PFID(ll_inode2fid(dir)), dir, filename,
+	       (int)lump->lum_stripe_offset, lump->lum_stripe_count);
+
+	if (lump->lum_magic != cpu_to_le32(LMV_USER_MAGIC))
+		lustre_swab_lmv_user_md(lump);
+
 	mode = (~current_umask() & 0755) | S_IFDIR;
 	op_data = ll_prep_md_op_data(NULL, dir, NULL, filename,
 				     strlen(filename), mode, LUSTRE_OPC_MKDIR,
@@ -745,9 +765,6 @@ int ll_dir_setstripe(struct inode *inode, struct lov_user_md *lump,
 	if (IS_ERR(op_data))
 		return PTR_ERR(op_data);
 
-	if (lump && lump->lmm_magic == cpu_to_le32(LMV_USER_MAGIC))
-		op_data->op_cli_flags |= CLI_SET_MEA;
-
 	/* swabbing is done in lov_setstripe() on server side */
 	rc = md_setattr(sbi->ll_md_exp, op_data, lump, lum_size,
 			NULL, 0, &req, NULL);
@@ -1424,7 +1441,6 @@ lmv_out_free:
 		}
 
 		*tmp = lum;
-		tmp->lum_type = LMV_STRIPE_TYPE;
 		tmp->lum_stripe_count = 1;
 		mdtindex = ll_get_mdt_idx(inode);
 		if (mdtindex < 0) {
diff --git a/drivers/staging/lustre/lustre/llite/file.c b/drivers/staging/lustre/lustre/llite/file.c
index 58a7401..18fb713 100644
--- a/drivers/staging/lustre/lustre/llite/file.c
+++ b/drivers/staging/lustre/lustre/llite/file.c
@@ -3015,6 +3015,27 @@ out:
 	return rc;
 }
 
+static int ll_merge_md_attr(struct inode *inode)
+{
+	struct cl_attr attr = { 0 };
+	int rc;
+
+	LASSERT(ll_i2info(inode)->lli_lsm_md);
+	rc = md_merge_attr(ll_i2mdexp(inode), ll_i2info(inode)->lli_lsm_md,
+			   &attr);
+	if (rc)
+		return rc;
+
+	ll_i2info(inode)->lli_stripe_dir_size = attr.cat_size;
+	ll_i2info(inode)->lli_stripe_dir_nlink = attr.cat_nlink;
+
+	ll_i2info(inode)->lli_atime = attr.cat_atime;
+	ll_i2info(inode)->lli_mtime = attr.cat_mtime;
+	ll_i2info(inode)->lli_ctime = attr.cat_ctime;
+
+	return 0;
+}
+
 static int ll_inode_revalidate(struct dentry *dentry, __u64 ibits)
 {
 	struct inode *inode = d_inode(dentry);
@@ -3026,6 +3047,13 @@ static int ll_inode_revalidate(struct dentry *dentry, __u64 ibits)
 
 	/* if object isn't regular file, don't validate size */
 	if (!S_ISREG(inode->i_mode)) {
+		if (S_ISDIR(inode->i_mode) &&
+		    ll_i2info(inode)->lli_lsm_md) {
+			rc = ll_merge_md_attr(inode);
+			if (rc)
+				return rc;
+		}
+
 		LTIME_S(inode->i_atime) = ll_i2info(inode)->lli_atime;
 		LTIME_S(inode->i_mtime) = ll_i2info(inode)->lli_mtime;
 		LTIME_S(inode->i_ctime) = ll_i2info(inode)->lli_ctime;
@@ -3063,7 +3091,6 @@ int ll_getattr(struct vfsmount *mnt, struct dentry *de, struct kstat *stat)
 	else
 		stat->ino = inode->i_ino;
 	stat->mode = inode->i_mode;
-	stat->nlink = inode->i_nlink;
 	stat->uid = inode->i_uid;
 	stat->gid = inode->i_gid;
 	stat->rdev = inode->i_rdev;
@@ -3071,10 +3098,17 @@ int ll_getattr(struct vfsmount *mnt, struct dentry *de, struct kstat *stat)
 	stat->mtime = inode->i_mtime;
 	stat->ctime = inode->i_ctime;
 	stat->blksize = 1 << inode->i_blkbits;
-
-	stat->size = i_size_read(inode);
 	stat->blocks = inode->i_blocks;
 
+	if (S_ISDIR(inode->i_mode) &&
+	    ll_i2info(inode)->lli_lsm_md) {
+		stat->nlink = lli->lli_stripe_dir_nlink;
+		stat->size = lli->lli_stripe_dir_size;
+	} else {
+		stat->nlink = inode->i_nlink;
+		stat->size = i_size_read(inode);
+	}
+
 	return 0;
 }
 
diff --git a/drivers/staging/lustre/lustre/llite/llite_internal.h b/drivers/staging/lustre/lustre/llite/llite_internal.h
index 07b6918..f3b8504 100644
--- a/drivers/staging/lustre/lustre/llite/llite_internal.h
+++ b/drivers/staging/lustre/lustre/llite/llite_internal.h
@@ -39,6 +39,7 @@
 
 /* for struct cl_lock_descr and struct cl_io */
 #include "../include/cl_object.h"
+#include "../include/lustre_lmv.h"
 #include "../include/lustre_mdc.h"
 #include "../include/lustre_intent.h"
 #include <linux/compat.h>
@@ -174,7 +175,11 @@ struct ll_inode_info {
 			 */
 			pid_t			   d_opendir_pid;
 			/* directory stripe information */
-			struct lmv_stripe_md		*d_lmv_md;
+			struct lmv_stripe_md		*d_lsm_md;
+			/* striped directory size */
+			loff_t				d_stripe_size;
+			/* striped directory nlink */
+			__u64				d_stripe_nlink;
 		} d;
 
 #define lli_readdir_mutex       u.d.d_readdir_mutex
@@ -182,7 +187,9 @@ struct ll_inode_info {
 #define lli_sai		 u.d.d_sai
 #define lli_sa_lock	     u.d.d_sa_lock
 #define lli_opendir_pid	 u.d.d_opendir_pid
-#define lli_lmv_md		u.d.d_lmv_md
+#define lli_lsm_md		u.d.d_lsm_md
+#define lli_stripe_dir_size	u.d.d_stripe_size
+#define lli_stripe_dir_nlink	u.d.d_stripe_nlink
 
 		/* for non-directory */
 		struct {
@@ -664,6 +671,7 @@ int ll_objects_destroy(struct ptlrpc_request *request,
 		       struct inode *dir);
 struct inode *ll_iget(struct super_block *sb, ino_t hash,
 		      struct lustre_md *lic);
+int ll_test_inode_by_fid(struct inode *inode, void *opaque);
 int ll_md_blocking_ast(struct ldlm_lock *, struct ldlm_lock_desc *,
 		       void *data, int flag);
 struct dentry *ll_splice_alias(struct inode *inode, struct dentry *de);
diff --git a/drivers/staging/lustre/lustre/llite/llite_lib.c b/drivers/staging/lustre/lustre/llite/llite_lib.c
index eb715be..ef8d87a 100644
--- a/drivers/staging/lustre/lustre/llite/llite_lib.c
+++ b/drivers/staging/lustre/lustre/llite/llite_lib.c
@@ -992,6 +992,188 @@ struct inode *ll_inode_from_resource_lock(struct ldlm_lock *lock)
 	return inode;
 }
 
+static void ll_dir_clear_lsm_md(struct inode *inode)
+{
+	struct ll_inode_info *lli = ll_i2info(inode);
+
+	LASSERT(S_ISDIR(inode->i_mode));
+
+	if (lli->lli_lsm_md) {
+		lmv_free_memmd(lli->lli_lsm_md);
+		lli->lli_lsm_md = NULL;
+	}
+}
+
+static struct inode *ll_iget_anon_dir(struct super_block *sb,
+				      const struct lu_fid *fid,
+				      struct lustre_md *md)
+{
+	struct ll_sb_info *sbi = ll_s2sbi(sb);
+	struct mdt_body *body = md->body;
+	struct inode *inode;
+	ino_t ino;
+
+	ino = cl_fid_build_ino(fid, sbi->ll_flags & LL_SBI_32BIT_API);
+	inode = iget_locked(sb, ino);
+	if (!inode) {
+		CERROR("%s: failed get simple inode "DFID": rc = -ENOENT\n",
+		       ll_get_fsname(sb, NULL, 0), PFID(fid));
+		return ERR_PTR(-ENOENT);
+	}
+
+	if (inode->i_state & I_NEW) {
+		struct ll_inode_info *lli = ll_i2info(inode);
+		struct lmv_stripe_md *lsm = md->lmv;
+
+		inode->i_mode = (inode->i_mode & ~S_IFMT) |
+				(body->mode & S_IFMT);
+		LASSERTF(S_ISDIR(inode->i_mode), "Not slave inode "DFID"\n",
+			 PFID(fid));
+
+		LTIME_S(inode->i_mtime) = 0;
+		LTIME_S(inode->i_atime) = 0;
+		LTIME_S(inode->i_ctime) = 0;
+		inode->i_rdev = 0;
+
+		inode->i_op = &ll_dir_inode_operations;
+		inode->i_fop = &ll_dir_operations;
+		lli->lli_fid = *fid;
+		ll_lli_init(lli);
+
+		LASSERT(lsm);
+		/* master stripe FID */
+		lli->lli_pfid = lsm->lsm_md_oinfo[0].lmo_fid;
+		CDEBUG(D_INODE, "lli %p master "DFID" slave "DFID"\n",
+		       lli, PFID(fid), PFID(&lli->lli_pfid));
+		unlock_new_inode(inode);
+	}
+
+	return inode;
+}
+
+static int ll_init_lsm_md(struct inode *inode, struct lustre_md *md)
+{
+	struct lmv_stripe_md *lsm = md->lmv;
+	struct lu_fid *fid;
+	int i;
+
+	LASSERT(lsm);
+	/*
+	 * XXX sigh, this lsm_root initialization should be in
+	 * LMV layer, but it needs ll_iget right now, so we
+	 * put this here right now.
+	 */
+	for (i = 0; i < lsm->lsm_md_stripe_count; i++) {
+		fid = &lsm->lsm_md_oinfo[i].lmo_fid;
+		LASSERT(!lsm->lsm_md_oinfo[i].lmo_root);
+		if (!i) {
+			lsm->lsm_md_oinfo[i].lmo_root = inode;
+		} else {
+			/*
+			 * Unfortunately ll_iget will call ll_update_inode,
+			 * where the initialization of slave inode is slightly
+			 * different, so it reset lsm_md to NULL to avoid
+			 * initializing lsm for slave inode.
+			 */
+			lsm->lsm_md_oinfo[i].lmo_root =
+				ll_iget_anon_dir(inode->i_sb, fid, md);
+			if (IS_ERR(lsm->lsm_md_oinfo[i].lmo_root)) {
+				int rc = PTR_ERR(lsm->lsm_md_oinfo[i].lmo_root);
+
+				lsm->lsm_md_oinfo[i].lmo_root = NULL;
+				return rc;
+			}
+		}
+	}
+
+	/*
+	 * Here is where the lsm is being initialized(fill lmo_info) after
+	 * client retrieve MD stripe information from MDT.
+	 */
+	return md_update_lsm_md(ll_i2mdexp(inode), lsm, md->body,
+				ll_md_blocking_ast);
+}
+
+static inline int lli_lsm_md_eq(const struct lmv_stripe_md *lsm_md1,
+				const struct lmv_stripe_md *lsm_md2)
+{
+	return lsm_md1->lsm_md_magic == lsm_md2->lsm_md_magic &&
+	       lsm_md1->lsm_md_stripe_count == lsm_md2->lsm_md_stripe_count &&
+	       lsm_md1->lsm_md_master_mdt_index ==
+			lsm_md2->lsm_md_master_mdt_index &&
+	       lsm_md1->lsm_md_hash_type == lsm_md2->lsm_md_hash_type &&
+	       lsm_md1->lsm_md_layout_version ==
+			lsm_md2->lsm_md_layout_version &&
+	       !strcmp(lsm_md1->lsm_md_pool_name,
+		       lsm_md2->lsm_md_pool_name);
+}
+
+static void ll_update_lsm_md(struct inode *inode, struct lustre_md *md)
+{
+	struct ll_inode_info *lli = ll_i2info(inode);
+	struct lmv_stripe_md *lsm = md->lmv;
+	int idx;
+
+	LASSERT(lsm);
+	LASSERT(S_ISDIR(inode->i_mode));
+	if (!lli->lli_lsm_md) {
+		int rc;
+
+		rc = ll_init_lsm_md(inode, md);
+		if (rc) {
+			CERROR("%s: init "DFID" failed: rc = %d\n",
+			       ll_get_fsname(inode->i_sb, NULL, 0),
+			       PFID(&lli->lli_fid), rc);
+			return;
+		}
+		lli->lli_lsm_md = lsm;
+		/*
+		 * set lsm_md to NULL, so the following free lustre_md
+		 * will not free this lsm
+		 */
+		md->lmv = NULL;
+		return;
+	}
+
+	/* Compare the old and new stripe information */
+	if (!lli_lsm_md_eq(lli->lli_lsm_md, lsm)) {
+		CERROR("inode %p %lu mismatch\n"
+		       "    new(%p)     vs     lli_lsm_md(%p):\n"
+		       "    magic:      %x                   %x\n"
+		       "    count:      %x                   %x\n"
+		       "    master:     %x                   %x\n"
+		       "    hash_type:  %x                   %x\n"
+		       "    layout:     %x                   %x\n"
+		       "    pool:       %s                   %s\n",
+		       inode, inode->i_ino, lsm, lli->lli_lsm_md,
+		       lsm->lsm_md_magic, lli->lli_lsm_md->lsm_md_magic,
+		       lsm->lsm_md_stripe_count,
+		       lli->lli_lsm_md->lsm_md_stripe_count,
+		       lsm->lsm_md_master_mdt_index,
+		       lli->lli_lsm_md->lsm_md_master_mdt_index,
+		       lsm->lsm_md_hash_type, lli->lli_lsm_md->lsm_md_hash_type,
+		       lsm->lsm_md_layout_version,
+		       lli->lli_lsm_md->lsm_md_layout_version,
+		       lsm->lsm_md_pool_name,
+		       lli->lli_lsm_md->lsm_md_pool_name);
+		return;
+	}
+
+	for (idx = 0; idx < lli->lli_lsm_md->lsm_md_stripe_count; idx++) {
+		if (!lu_fid_eq(&lli->lli_lsm_md->lsm_md_oinfo[idx].lmo_fid,
+			       &lsm->lsm_md_oinfo[idx].lmo_fid)) {
+			CERROR("%s: FID in lsm mismatch idx %d, old: "DFID" new:"DFID"\n",
+			       ll_get_fsname(inode->i_sb, NULL, 0), idx,
+			       PFID(&lli->lli_lsm_md->lsm_md_oinfo[idx].lmo_fid),
+			       PFID(&lsm->lsm_md_oinfo[idx].lmo_fid));
+			return;
+		}
+	}
+
+	md_update_lsm_md(ll_i2mdexp(inode), ll_i2info(inode)->lli_lsm_md,
+			 md->body, ll_md_blocking_ast);
+}
+
 void ll_clear_inode(struct inode *inode)
 {
 	struct ll_inode_info *lli = ll_i2info(inode);
@@ -1039,7 +1221,9 @@ void ll_clear_inode(struct inode *inode)
 #endif
 	lli->lli_inode_magic = LLI_INODE_DEAD;
 
-	if (!S_ISDIR(inode->i_mode))
+	if (S_ISDIR(inode->i_mode))
+		ll_dir_clear_lsm_md(inode);
+	else
 		LASSERT(list_empty(&lli->lli_agl_list));
 
 	/*
@@ -1484,6 +1668,9 @@ void ll_update_inode(struct inode *inode, struct lustre_md *md)
 			lli->lli_maxbytes = MAX_LFS_FILESIZE;
 	}
 
+	if (S_ISDIR(inode->i_mode) && md->lmv)
+		ll_update_lsm_md(inode, md);
+
 #ifdef CONFIG_FS_POSIX_ACL
 	if (body->valid & OBD_MD_FLACL) {
 		spin_lock(&lli->lli_lock);
@@ -2091,12 +2278,12 @@ struct md_op_data *ll_prep_md_op_data(struct md_op_data *op_data,
 	ll_i2gids(op_data->op_suppgids, i1, i2);
 	op_data->op_fid1 = *ll_inode2fid(i1);
 	if (S_ISDIR(i1->i_mode))
-		op_data->op_mea1 = ll_i2info(i1)->lli_lmv_md;
+		op_data->op_mea1 = ll_i2info(i1)->lli_lsm_md;
 
 	if (i2) {
 		op_data->op_fid2 = *ll_inode2fid(i2);
 		if (S_ISDIR(i2->i_mode))
-			op_data->op_mea2 = ll_i2info(i2)->lli_lmv_md;
+			op_data->op_mea2 = ll_i2info(i2)->lli_lsm_md;
 	} else {
 		fid_zero(&op_data->op_fid2);
 	}
diff --git a/drivers/staging/lustre/lustre/llite/llite_nfs.c b/drivers/staging/lustre/lustre/llite/llite_nfs.c
index 74eb1fc..ab9d5cc 100644
--- a/drivers/staging/lustre/lustre/llite/llite_nfs.c
+++ b/drivers/staging/lustre/lustre/llite/llite_nfs.c
@@ -73,11 +73,6 @@ void get_uuid2fsid(const char *name, int len, __kernel_fsid_t *fsid)
 	fsid->val[1] = key >> 32;
 }
 
-static int ll_nfs_test_inode(struct inode *inode, void *opaque)
-{
-	return lu_fid_eq(&ll_i2info(inode)->lli_fid, opaque);
-}
-
 struct inode *search_inode_for_lustre(struct super_block *sb,
 				      const struct lu_fid *fid)
 {
@@ -92,7 +87,7 @@ struct inode *search_inode_for_lustre(struct super_block *sb,
 
 	CDEBUG(D_INFO, "searching inode for:(%lu,"DFID")\n", hash, PFID(fid));
 
-	inode = ilookup5(sb, hash, ll_nfs_test_inode, (void *)fid);
+	inode = ilookup5(sb, hash, ll_test_inode_by_fid, (void *)fid);
 	if (inode)
 		return inode;
 
diff --git a/drivers/staging/lustre/lustre/llite/namei.c b/drivers/staging/lustre/lustre/llite/namei.c
index 1e75f5b..e32d08b 100644
--- a/drivers/staging/lustre/lustre/llite/namei.c
+++ b/drivers/staging/lustre/lustre/llite/namei.c
@@ -158,6 +158,11 @@ static void ll_invalidate_negative_children(struct inode *dir)
 	spin_unlock(&dir->i_lock);
 }
 
+int ll_test_inode_by_fid(struct inode *inode, void *opaque)
+{
+	return lu_fid_eq(&ll_i2info(inode)->lli_fid, opaque);
+}
+
 int ll_md_blocking_ast(struct ldlm_lock *lock, struct ldlm_lock_desc *desc,
 		       void *data, int flag)
 {
@@ -253,10 +258,41 @@ int ll_md_blocking_ast(struct ldlm_lock *lock, struct ldlm_lock_desc *desc,
 		}
 
 		if ((bits & MDS_INODELOCK_UPDATE) && S_ISDIR(inode->i_mode)) {
-			CDEBUG(D_INODE, "invalidating inode "DFID"\n",
-			       PFID(ll_inode2fid(inode)));
+			struct ll_inode_info *lli = ll_i2info(inode);
+
+			CDEBUG(D_INODE, "invalidating inode "DFID" lli = %p, pfid  = "DFID"\n",
+			       PFID(ll_inode2fid(inode)), lli,
+			       PFID(&lli->lli_pfid));
+
 			truncate_inode_pages(inode->i_mapping, 0);
-			ll_invalidate_negative_children(inode);
+
+			if (unlikely(!fid_is_zero(&lli->lli_pfid))) {
+				struct inode *master_inode = NULL;
+				unsigned long hash;
+
+				/*
+				 * This is slave inode, since all of the child
+				 * dentry is connected on the master inode, so
+				 * we have to invalidate the negative children
+				 * on master inode
+				 */
+				CDEBUG(D_INODE, "Invalidate s"DFID" m"DFID"\n",
+				       PFID(ll_inode2fid(inode)),
+				       PFID(&lli->lli_pfid));
+
+				hash = cl_fid_build_ino(&lli->lli_pfid,
+							ll_need_32bit_api(ll_i2sbi(inode)));
+
+				master_inode = ilookup5(inode->i_sb, hash,
+							ll_test_inode_by_fid,
+							(void *)&lli->lli_pfid);
+				if (master_inode && !IS_ERR(master_inode)) {
+					ll_invalidate_negative_children(master_inode);
+					iput(master_inode);
+				}
+			} else {
+				ll_invalidate_negative_children(inode);
+			}
 		}
 
 		if ((bits & (MDS_INODELOCK_LOOKUP | MDS_INODELOCK_PERM)) &&
diff --git a/drivers/staging/lustre/lustre/lmv/lmv_intent.c b/drivers/staging/lustre/lustre/lmv/lmv_intent.c
index 2f58fda..1b9bbb2 100644
--- a/drivers/staging/lustre/lustre/lmv/lmv_intent.c
+++ b/drivers/staging/lustre/lustre/lmv/lmv_intent.c
@@ -150,6 +150,160 @@ out:
 	return rc;
 }
 
+int lmv_revalidate_slaves(struct obd_export *exp, struct mdt_body *mbody,
+			  struct lmv_stripe_md *lsm,
+			  ldlm_blocking_callback cb_blocking,
+			  int extra_lock_flags)
+{
+	struct obd_device *obd = exp->exp_obd;
+	struct lmv_obd *lmv = &obd->u.lmv;
+	struct mdt_body *body;
+	struct md_op_data *op_data;
+	unsigned long size = 0;
+	unsigned long nlink = 0;
+	__s64 atime = 0;
+	__s64 ctime = 0;
+	__s64 mtime = 0;
+	int rc = 0, i;
+
+	/**
+	 * revalidate slaves has some problems, temporarily return,
+	 * we may not need that
+	 */
+	if (lsm->lsm_md_stripe_count <= 1)
+		return 0;
+
+	op_data = kzalloc(sizeof(*op_data), GFP_NOFS);
+	if (!op_data)
+		return -ENOMEM;
+
+	/**
+	 * Loop over the stripe information, check validity and update them
+	 * from MDS if needed.
+	 */
+	for (i = 0; i < lsm->lsm_md_stripe_count; i++) {
+		struct lookup_intent it = { .it_op = IT_GETATTR };
+		struct ptlrpc_request *req = NULL;
+		struct lustre_handle *lockh = NULL;
+		struct lmv_tgt_desc *tgt = NULL;
+		struct inode *inode;
+		struct lu_fid fid;
+
+		fid = lsm->lsm_md_oinfo[i].lmo_fid;
+		inode = lsm->lsm_md_oinfo[i].lmo_root;
+		if (!i) {
+			if (mbody) {
+				body = mbody;
+				goto update;
+			} else {
+				goto release_lock;
+			}
+		}
+
+		/*
+		 * Prepare op_data for revalidating. Note that @fid2 shluld be
+		 * defined otherwise it will go to server and take new lock
+		 * which is not needed here.
+		 */
+		memset(op_data, 0, sizeof(*op_data));
+		op_data->op_fid1 = fid;
+		op_data->op_fid2 = fid;
+
+		tgt = lmv_locate_mds(lmv, op_data, &fid);
+		if (IS_ERR(tgt)) {
+			rc = PTR_ERR(tgt);
+			goto cleanup;
+		}
+
+		CDEBUG(D_INODE, "Revalidate slave "DFID" -> mds #%d\n",
+		       PFID(&fid), tgt->ltd_idx);
+
+		rc = md_intent_lock(tgt->ltd_exp, op_data, NULL, 0, &it, 0,
+				    &req, cb_blocking, extra_lock_flags);
+		if (rc < 0)
+			goto cleanup;
+
+		lockh = (struct lustre_handle *)&it.it_lock_handle;
+		if (rc > 0 && !req) {
+			/* slave inode is still valid */
+			CDEBUG(D_INODE, "slave "DFID" is still valid.\n",
+			       PFID(&fid));
+			rc = 0;
+		} else {
+			/* refresh slave from server */
+			body = req_capsule_server_get(&req->rq_pill,
+						      &RMF_MDT_BODY);
+			LASSERT(body);
+update:
+			if (unlikely(body->nlink < 2)) {
+				CERROR("%s: nlink %d < 2 corrupt stripe %d "DFID":" DFID"\n",
+				       obd->obd_name, body->nlink, i,
+				       PFID(&lsm->lsm_md_oinfo[i].lmo_fid),
+				       PFID(&lsm->lsm_md_oinfo[0].lmo_fid));
+
+				if (req)
+					ptlrpc_req_finished(req);
+
+				rc = -EIO;
+				goto cleanup;
+			}
+
+			if (i)
+				md_set_lock_data(tgt->ltd_exp, &lockh->cookie,
+						 inode, NULL);
+
+			i_size_write(inode, body->size);
+			set_nlink(inode, body->nlink);
+			LTIME_S(inode->i_atime) = body->atime;
+			LTIME_S(inode->i_ctime) = body->ctime;
+			LTIME_S(inode->i_mtime) = body->mtime;
+
+			if (req)
+				ptlrpc_req_finished(req);
+		}
+release_lock:
+		size += i_size_read(inode);
+
+		if (i != 0)
+			nlink += inode->i_nlink - 2;
+		else
+			nlink += inode->i_nlink;
+
+		atime = LTIME_S(inode->i_atime) > atime ?
+				LTIME_S(inode->i_atime) : atime;
+		ctime = LTIME_S(inode->i_ctime) > ctime ?
+				LTIME_S(inode->i_ctime) : ctime;
+		mtime = LTIME_S(inode->i_mtime) > mtime ?
+				LTIME_S(inode->i_mtime) : mtime;
+
+		if (it.it_lock_mode && lockh) {
+			ldlm_lock_decref(lockh, it.it_lock_mode);
+			it.it_lock_mode = 0;
+		}
+
+		CDEBUG(D_INODE, "i %d "DFID" size %llu, nlink %u, atime %lu, mtime %lu, ctime %lu.\n",
+		       i, PFID(&fid), i_size_read(inode), inode->i_nlink,
+		       LTIME_S(inode->i_atime), LTIME_S(inode->i_mtime),
+		       LTIME_S(inode->i_ctime));
+	}
+
+	/*
+	 * update attr of master request.
+	 */
+	CDEBUG(D_INODE, "Return refreshed attrs: size = %lu nlink %lu atime %llu ctime %llu mtime %llu for " DFID"\n",
+	       size, nlink, atime, ctime, mtime,
+	       PFID(&lsm->lsm_md_oinfo[0].lmo_fid));
+
+	if (mbody) {
+		mbody->atime = atime;
+		mbody->ctime = ctime;
+		mbody->mtime = mtime;
+	}
+cleanup:
+	kfree(op_data);
+	return rc;
+}
+
 /*
  * IT_OPEN is intended to open (and create, possible) an object. Parent (pid)
  * may be split dir.
@@ -166,9 +320,26 @@ static int lmv_intent_open(struct obd_export *exp, struct md_op_data *op_data,
 	struct mdt_body		*body;
 	int			rc;
 
-	tgt = lmv_locate_mds(lmv, op_data, &op_data->op_fid1);
-	if (IS_ERR(tgt))
-		return PTR_ERR(tgt);
+	if (it->it_flags & MDS_OPEN_BY_FID && fid_is_sane(&op_data->op_fid2)) {
+		if (op_data->op_mea1) {
+			struct lmv_stripe_md *lsm = op_data->op_mea1;
+			const struct lmv_oinfo *oinfo;
+
+			oinfo = lsm_name_to_stripe_info(lsm, op_data->op_name,
+							op_data->op_namelen);
+			op_data->op_fid1 = oinfo->lmo_fid;
+		}
+
+		tgt = lmv_find_target(lmv, &op_data->op_fid2);
+		if (IS_ERR(tgt))
+			return PTR_ERR(tgt);
+
+		op_data->op_mds = tgt->ltd_idx;
+	} else {
+		tgt = lmv_locate_mds(lmv, op_data, &op_data->op_fid1);
+		if (IS_ERR(tgt))
+			return PTR_ERR(tgt);
+	}
 
 	/* If it is ready to open the file by FID, do not need
 	 * allocate FID at all, otherwise it will confuse MDT
@@ -205,31 +376,18 @@ static int lmv_intent_open(struct obd_export *exp, struct md_op_data *op_data,
 	body = req_capsule_server_get(&(*reqp)->rq_pill, &RMF_MDT_BODY);
 	if (!body)
 		return -EPROTO;
-	/*
-	 * Not cross-ref case, just get out of here.
-	 */
-	if (likely(!(body->valid & OBD_MD_MDS)))
-		return 0;
 
-	/*
-	 * Okay, MDS has returned success. Probably name has been resolved in
-	 * remote inode.
-	 */
-	rc = lmv_intent_remote(exp, lmm, lmmsize, it, &op_data->op_fid1, flags,
-			       reqp, cb_blocking, extra_lock_flags);
-	if (rc != 0) {
-		LASSERT(rc < 0);
-		/*
-		 * This is possible, that some userspace application will try to
-		 * open file as directory and we will have -ENOTDIR here. As
-		 * this is normal situation, we should not print error here,
-		 * only debug info.
-		 */
-		CDEBUG(D_INODE, "Can't handle remote %s: dir " DFID "(" DFID "):%*s: %d\n",
-		       LL_IT2STR(it), PFID(&op_data->op_fid2),
-		       PFID(&op_data->op_fid1), op_data->op_namelen,
-		       op_data->op_name, rc);
-		return rc;
+	/* Not cross-ref case, just get out of here. */
+	if (unlikely((body->valid & OBD_MD_MDS))) {
+		rc = lmv_intent_remote(exp, lmm, lmmsize, it, &op_data->op_fid1,
+				       flags, reqp, cb_blocking,
+				       extra_lock_flags);
+		if (rc != 0)
+			return rc;
+
+		body = req_capsule_server_get(&(*reqp)->rq_pill, &RMF_MDT_BODY);
+		if (!body)
+			return -EPROTO;
 	}
 
 	return rc;
@@ -269,8 +427,23 @@ static int lmv_intent_lookup(struct obd_export *exp,
 	rc = md_intent_lock(tgt->ltd_exp, op_data, lmm, lmmsize, it,
 			    flags, reqp, cb_blocking, extra_lock_flags);
 
-	if (rc < 0 || !*reqp)
+	if (rc < 0)
+		return rc;
+
+	if (!*reqp) {
+		/*
+		 * If RPC happens, lsm information will be revalidated
+		 * during update_inode process (see ll_update_lsm_md)
+		 */
+		if (op_data->op_mea2) {
+			rc = lmv_revalidate_slaves(exp, NULL, op_data->op_mea2,
+						   cb_blocking,
+						   extra_lock_flags);
+			if (rc != 0)
+				return rc;
+		}
 		return rc;
+	}
 
 	/*
 	 * MDS has returned success. Probably name has been resolved in
@@ -279,12 +452,17 @@ static int lmv_intent_lookup(struct obd_export *exp,
 	body = req_capsule_server_get(&(*reqp)->rq_pill, &RMF_MDT_BODY);
 	if (!body)
 		return -EPROTO;
-	/* Not cross-ref case, just get out of here. */
-	if (likely(!(body->valid & OBD_MD_MDS)))
-		return 0;
 
-	rc = lmv_intent_remote(exp, lmm, lmmsize, it, NULL, flags, reqp,
-			       cb_blocking, extra_lock_flags);
+	/* Not cross-ref case, just get out of here. */
+	if (unlikely((body->valid & OBD_MD_MDS))) {
+		rc = lmv_intent_remote(exp, lmm, lmmsize, it, NULL, flags,
+				       reqp, cb_blocking, extra_lock_flags);
+		if (rc != 0)
+			return rc;
+		body = req_capsule_server_get(&(*reqp)->rq_pill, &RMF_MDT_BODY);
+		if (!body)
+			return -EPROTO;
+	}
 
 	return rc;
 }
diff --git a/drivers/staging/lustre/lustre/lmv/lmv_internal.h b/drivers/staging/lustre/lustre/lmv/lmv_internal.h
index f4c917b..ed02927 100644
--- a/drivers/staging/lustre/lustre/lmv/lmv_internal.h
+++ b/drivers/staging/lustre/lustre/lmv/lmv_internal.h
@@ -55,6 +55,14 @@ int __lmv_fid_alloc(struct lmv_obd *lmv, struct lu_fid *fid, u32 mds);
 int lmv_fid_alloc(struct obd_export *exp, struct lu_fid *fid,
 		  struct md_op_data *op_data);
 
+int lmv_unpack_md(struct obd_export *exp, struct lmv_stripe_md **lsmp,
+		  const union lmv_mds_md *lmm, int stripe_count);
+
+int lmv_revalidate_slaves(struct obd_export *exp, struct mdt_body *mbody,
+			  struct lmv_stripe_md *lsm,
+			  ldlm_blocking_callback cb_blocking,
+			  int extra_lock_flags);
+
 static inline struct lmv_tgt_desc *
 lmv_get_target(struct lmv_obd *lmv, u32 mds)
 {
@@ -94,6 +102,30 @@ static inline int lmv_stripe_md_size(int stripe_count)
 	return sizeof(*lsm) + stripe_count * sizeof(lsm->lsm_md_oinfo[0]);
 }
 
+int lmv_name_to_stripe_index(enum lmv_hash_type hashtype,
+			     unsigned int max_mdt_index,
+			     const char *name, int namelen);
+
+static inline const struct lmv_oinfo *
+lsm_name_to_stripe_info(const struct lmv_stripe_md *lsm, const char *name,
+			int namelen)
+{
+	int stripe_index;
+
+	stripe_index = lmv_name_to_stripe_index(lsm->lsm_md_hash_type,
+						lsm->lsm_md_stripe_count,
+						name, namelen);
+	if (stripe_index < 0)
+		return ERR_PTR(stripe_index);
+
+	LASSERTF(stripe_index < lsm->lsm_md_stripe_count,
+		 "stripe_index = %d, stripe_count = %d hash_type = %x name = %.*s\n",
+		 stripe_index, lsm->lsm_md_stripe_count,
+		 lsm->lsm_md_hash_type, namelen, name);
+
+	return &lsm->lsm_md_oinfo[stripe_index];
+}
+
 struct lmv_tgt_desc
 *lmv_locate_mds(struct lmv_obd *lmv, struct md_op_data *op_data,
 		struct lu_fid *fid);
diff --git a/drivers/staging/lustre/lustre/lmv/lmv_obd.c b/drivers/staging/lustre/lustre/lmv/lmv_obd.c
index 6be2afc..da4855d 100644
--- a/drivers/staging/lustre/lustre/lmv/lmv_obd.c
+++ b/drivers/staging/lustre/lustre/lmv/lmv_obd.c
@@ -48,11 +48,63 @@
 #include "../include/obd_class.h"
 #include "../include/lustre_lmv.h"
 #include "../include/lprocfs_status.h"
+#include "../include/cl_object.h"
 #include "../include/lustre_lite.h"
 #include "../include/lustre_fid.h"
 #include "../include/lustre_kernelcomm.h"
 #include "lmv_internal.h"
 
+/* This hash is only for testing purpose */
+static inline unsigned int
+lmv_hash_all_chars(unsigned int count, const char *name, int namelen)
+{
+	const unsigned char *p = (const unsigned char *)name;
+	unsigned int c = 0;
+
+	while (--namelen >= 0)
+		c += p[namelen];
+
+	c = c % count;
+
+	return c;
+}
+
+static inline unsigned int
+lmv_hash_fnv1a(unsigned int count, const char *name, int namelen)
+{
+	__u64 hash;
+
+	hash = lustre_hash_fnv_1a_64(name, namelen);
+
+	return do_div(hash, count);
+}
+
+int lmv_name_to_stripe_index(enum lmv_hash_type hashtype,
+			     unsigned int max_mdt_index,
+			     const char *name, int namelen)
+{
+	int idx;
+
+	LASSERT(namelen > 0);
+	if (max_mdt_index <= 1)
+		return 0;
+
+	switch (hashtype) {
+	case LMV_HASH_TYPE_ALL_CHARS:
+		idx = lmv_hash_all_chars(max_mdt_index, name, namelen);
+		break;
+	case LMV_HASH_TYPE_FNV_1A_64:
+		idx = lmv_hash_fnv1a(max_mdt_index, name, namelen);
+		break;
+	default:
+		CERROR("Unknown hash type 0x%x\n", hashtype);
+		return -EINVAL;
+	}
+
+	LASSERT(idx < max_mdt_index);
+	return idx;
+}
+
 static void lmv_activate_target(struct lmv_obd *lmv,
 				struct lmv_tgt_desc *tgt,
 				int activate)
@@ -1174,28 +1226,19 @@ static int lmv_placement_policy(struct obd_device *obd,
 	 * If stripe_offset is provided during setdirstripe
 	 * (setdirstripe -i xx), xx MDS will be chosen.
 	 */
-	if (op_data->op_cli_flags & CLI_SET_MEA) {
+	if (op_data->op_cli_flags & CLI_SET_MEA && op_data->op_data) {
 		struct lmv_user_md *lum;
 
-		lum = (struct lmv_user_md *)op_data->op_data;
-		if (lum->lum_type == LMV_STRIPE_TYPE &&
-		    lum->lum_stripe_offset != -1) {
-			if (lum->lum_stripe_offset >= lmv->desc.ld_tgt_count) {
-				CERROR("%s: Stripe_offset %d > MDT count %d: rc = %d\n",
-				       obd->obd_name,
-				       lum->lum_stripe_offset,
-				       lmv->desc.ld_tgt_count, -ERANGE);
-				return -ERANGE;
-			}
-			*mds = lum->lum_stripe_offset;
-			return 0;
-		}
+		lum = op_data->op_data;
+		*mds = lum->lum_stripe_offset;
+	} else {
+		/*
+		 * Allocate new fid on target according to operation type and
+		 * parent home mds.
+		 */
+		*mds = op_data->op_mds;
 	}
 
-	/* Allocate new fid on target according to operation type and parent
-	 * home mds.
-	 */
-	*mds = op_data->op_mds;
 	return 0;
 }
 
@@ -1597,17 +1640,38 @@ static int lmv_close(struct obd_export *exp, struct md_op_data *op_data,
 	return rc;
 }
 
+/**
+ * Choosing the MDT by name or FID in @op_data.
+ * For non-striped directory, it will locate MDT by fid.
+ * For striped-directory, it will locate MDT by name. And also
+ * it will reset op_fid1 with the FID of the chosen stripe.
+ **/
 struct lmv_tgt_desc
 *lmv_locate_mds(struct lmv_obd *lmv, struct md_op_data *op_data,
 		struct lu_fid *fid)
 {
+	struct lmv_stripe_md *lsm = op_data->op_mea1;
+	const struct lmv_oinfo *oinfo;
 	struct lmv_tgt_desc *tgt;
 
-	tgt = lmv_find_target(lmv, fid);
-	if (IS_ERR(tgt))
+	if (!lsm || lsm->lsm_md_stripe_count <= 1 ||
+	    !op_data->op_namelen) {
+		tgt = lmv_find_target(lmv, fid);
+		if (IS_ERR(tgt))
+			return tgt;
+
+		op_data->op_mds = tgt->ltd_idx;
+
 		return tgt;
+	}
 
-	op_data->op_mds = tgt->ltd_idx;
+	oinfo = lsm_name_to_stripe_info(lsm, op_data->op_name,
+					op_data->op_namelen);
+	*fid = oinfo->lmo_fid;
+	op_data->op_mds = oinfo->lmo_mds;
+	tgt = lmv_get_target(lmv, op_data->op_mds);
+
+	CDEBUG(D_INFO, "locate on mds %u\n", op_data->op_mds);
 
 	return tgt;
 }
@@ -1633,13 +1697,26 @@ static int lmv_create(struct obd_export *exp, struct md_op_data *op_data,
 	if (IS_ERR(tgt))
 		return PTR_ERR(tgt);
 
+	CDEBUG(D_INODE, "CREATE name '%.*s' on "DFID" -> mds #%x\n",
+	       op_data->op_namelen, op_data->op_name, PFID(&op_data->op_fid1),
+	       op_data->op_mds);
+
 	rc = lmv_fid_alloc(exp, &op_data->op_fid2, op_data);
 	if (rc)
 		return rc;
 
-	CDEBUG(D_INODE, "CREATE '%*s' on "DFID" -> mds #%x\n",
-	       op_data->op_namelen, op_data->op_name, PFID(&op_data->op_fid1),
-	       op_data->op_mds);
+	/*
+	 * Send the create request to the MDT where the object
+	 * will be located
+	 */
+	tgt = lmv_find_target(lmv, &op_data->op_fid2);
+	if (IS_ERR(tgt))
+		return PTR_ERR(tgt);
+
+	op_data->op_mds = tgt->ltd_idx;
+
+	CDEBUG(D_INODE, "CREATE obj "DFID" -> mds #%x\n",
+	       PFID(&op_data->op_fid1), op_data->op_mds);
 
 	op_data->op_flags |= MF_MDC_CANCEL_FID1;
 	rc = md_create(tgt->ltd_exp, op_data, data, datalen, mode, uid, gid,
@@ -1889,6 +1966,15 @@ static int lmv_link(struct obd_export *exp, struct md_op_data *op_data,
 	op_data->op_fsuid = from_kuid(&init_user_ns, current_fsuid());
 	op_data->op_fsgid = from_kgid(&init_user_ns, current_fsgid());
 	op_data->op_cap = cfs_curproc_cap_pack();
+	if (op_data->op_mea2) {
+		struct lmv_stripe_md *lsm = op_data->op_mea2;
+		const struct lmv_oinfo *oinfo;
+
+		oinfo = lsm_name_to_stripe_info(lsm, op_data->op_name,
+						op_data->op_namelen);
+		op_data->op_fid2 = oinfo->lmo_fid;
+	}
+
 	tgt = lmv_locate_mds(lmv, op_data, &op_data->op_fid2);
 	if (IS_ERR(tgt))
 		return PTR_ERR(tgt);
@@ -1914,14 +2000,15 @@ static int lmv_rename(struct obd_export *exp, struct md_op_data *op_data,
 	struct obd_device       *obd = exp->exp_obd;
 	struct lmv_obd	  *lmv = &obd->u.lmv;
 	struct lmv_tgt_desc     *src_tgt;
-	struct lmv_tgt_desc     *tgt_tgt;
 	int			rc;
 
 	LASSERT(oldlen != 0);
 
-	CDEBUG(D_INODE, "RENAME %*s in "DFID" to %*s in "DFID"\n",
+	CDEBUG(D_INODE, "RENAME %.*s in "DFID":%d to %.*s in "DFID":%d\n",
 	       oldlen, old, PFID(&op_data->op_fid1),
-	       newlen, new, PFID(&op_data->op_fid2));
+	       op_data->op_mea1 ? op_data->op_mea1->lsm_md_stripe_count : 0,
+	       newlen, new, PFID(&op_data->op_fid2),
+	       op_data->op_mea2 ? op_data->op_mea2->lsm_md_stripe_count : 0);
 
 	rc = lmv_check_connect(obd);
 	if (rc)
@@ -1930,13 +2017,33 @@ static int lmv_rename(struct obd_export *exp, struct md_op_data *op_data,
 	op_data->op_fsuid = from_kuid(&init_user_ns, current_fsuid());
 	op_data->op_fsgid = from_kgid(&init_user_ns, current_fsgid());
 	op_data->op_cap = cfs_curproc_cap_pack();
-	src_tgt = lmv_locate_mds(lmv, op_data, &op_data->op_fid1);
-	if (IS_ERR(src_tgt))
-		return PTR_ERR(src_tgt);
 
-	tgt_tgt = lmv_locate_mds(lmv, op_data, &op_data->op_fid2);
-	if (IS_ERR(tgt_tgt))
-		return PTR_ERR(tgt_tgt);
+	if (op_data->op_mea1) {
+		struct lmv_stripe_md *lsm = op_data->op_mea1;
+		const struct lmv_oinfo *oinfo;
+
+		oinfo = lsm_name_to_stripe_info(lsm, old, oldlen);
+		op_data->op_fid1 = oinfo->lmo_fid;
+		op_data->op_mds = oinfo->lmo_mds;
+		src_tgt = lmv_get_target(lmv, op_data->op_mds);
+		if (IS_ERR(src_tgt))
+			return PTR_ERR(src_tgt);
+	} else {
+		src_tgt = lmv_find_target(lmv, &op_data->op_fid1);
+		if (IS_ERR(src_tgt))
+			return PTR_ERR(src_tgt);
+
+		op_data->op_mds = src_tgt->ltd_idx;
+	}
+
+	if (op_data->op_mea2) {
+		struct lmv_stripe_md *lsm = op_data->op_mea2;
+		const struct lmv_oinfo *oinfo;
+
+		oinfo = lsm_name_to_stripe_info(lsm, new, newlen);
+		op_data->op_fid2 = oinfo->lmo_fid;
+	}
+
 	/*
 	 * LOOKUP lock on src child (fid3) should also be cancelled for
 	 * src_tgt in mdc_rename.
@@ -2568,6 +2675,7 @@ int lmv_unpack_md(struct obd_export *exp, struct lmv_stripe_md **lsmp,
 	}
 	return lsm_size;
 }
+EXPORT_SYMBOL(lmv_unpack_md);
 
 int lmv_unpackmd(struct obd_export *exp, struct lov_stripe_md **lsmp,
 		 struct lov_mds_md *lmm, int disk_len)
@@ -2741,7 +2849,7 @@ static int lmv_intent_getattr_async(struct obd_export *exp,
 	if (rc)
 		return rc;
 
-	tgt = lmv_find_target(lmv, &op_data->op_fid1);
+	tgt = lmv_locate_mds(lmv, op_data, &op_data->op_fid1);
 	if (IS_ERR(tgt))
 		return PTR_ERR(tgt);
 
@@ -2843,6 +2951,49 @@ static int lmv_quotacheck(struct obd_device *unused, struct obd_export *exp,
 	return rc;
 }
 
+int lmv_update_lsm_md(struct obd_export *exp, struct lmv_stripe_md *lsm,
+		      struct mdt_body *body, ldlm_blocking_callback cb_blocking)
+{
+	if (lsm->lsm_md_stripe_count <= 1)
+		return 0;
+
+	return lmv_revalidate_slaves(exp, body, lsm, cb_blocking, 0);
+}
+
+int lmv_merge_attr(struct obd_export *exp, const struct lmv_stripe_md *lsm,
+		   struct cl_attr *attr)
+{
+	int i;
+
+	for (i = 0; i < lsm->lsm_md_stripe_count; i++) {
+		struct inode *inode = lsm->lsm_md_oinfo[i].lmo_root;
+
+		CDEBUG(D_INFO, ""DFID" size %llu, nlink %u, atime %lu ctime %lu, mtime %lu.\n",
+		       PFID(&lsm->lsm_md_oinfo[i].lmo_fid),
+		       i_size_read(inode), inode->i_nlink,
+		       LTIME_S(inode->i_atime), LTIME_S(inode->i_ctime),
+		       LTIME_S(inode->i_mtime));
+
+		/* for slave stripe, it needs to subtract nlink for . and .. */
+		if (i)
+			attr->cat_nlink += inode->i_nlink - 2;
+		else
+			attr->cat_nlink = inode->i_nlink;
+
+		attr->cat_size += i_size_read(inode);
+
+		if (attr->cat_atime < LTIME_S(inode->i_atime))
+			attr->cat_atime = LTIME_S(inode->i_atime);
+
+		if (attr->cat_ctime < LTIME_S(inode->i_ctime))
+			attr->cat_ctime = LTIME_S(inode->i_ctime);
+
+		if (attr->cat_mtime < LTIME_S(inode->i_mtime))
+			attr->cat_mtime = LTIME_S(inode->i_mtime);
+	}
+	return 0;
+}
+
 static struct obd_ops lmv_obd_ops = {
 	.owner		= THIS_MODULE,
 	.setup		= lmv_setup,
@@ -2888,6 +3039,8 @@ static struct md_ops lmv_md_ops = {
 	.lock_match		= lmv_lock_match,
 	.get_lustre_md		= lmv_get_lustre_md,
 	.free_lustre_md		= lmv_free_lustre_md,
+	.update_lsm_md		= lmv_update_lsm_md,
+	.merge_attr		= lmv_merge_attr,
 	.set_open_replay_data	= lmv_set_open_replay_data,
 	.clear_open_replay_data	= lmv_clear_open_replay_data,
 	.intent_getattr_async	= lmv_intent_getattr_async,
diff --git a/drivers/staging/lustre/lustre/mdc/mdc_locks.c b/drivers/staging/lustre/lustre/mdc/mdc_locks.c
index 06a1274..626fce5 100644
--- a/drivers/staging/lustre/lustre/mdc/mdc_locks.c
+++ b/drivers/staging/lustre/lustre/mdc/mdc_locks.c
@@ -325,6 +325,9 @@ static struct ptlrpc_request *mdc_intent_open_pack(struct obd_export *exp,
 	mdc_open_pack(req, op_data, it->it_create_mode, 0, it->it_flags, lmm,
 		      lmmsize);
 
+	req_capsule_set_size(&req->rq_pill, &RMF_MDT_MD, RCL_SERVER,
+			     obddev->u.cli.cl_max_mds_easize);
+
 	ptlrpc_request_set_replen(req);
 	return req;
 }
diff --git a/drivers/staging/lustre/lustre/ptlrpc/pack_generic.c b/drivers/staging/lustre/lustre/ptlrpc/pack_generic.c
index b514f18..07e23d1 100644
--- a/drivers/staging/lustre/lustre/ptlrpc/pack_generic.c
+++ b/drivers/staging/lustre/lustre/ptlrpc/pack_generic.c
@@ -1878,6 +1878,17 @@ void lustre_swab_lov_desc(struct lov_desc *ld)
 }
 EXPORT_SYMBOL(lustre_swab_lov_desc);
 
+void lustre_swab_lmv_user_md(struct lmv_user_md *lum)
+{
+	__swab32s(&lum->lum_magic);
+	__swab32s(&lum->lum_stripe_count);
+	__swab32s(&lum->lum_stripe_offset);
+	__swab32s(&lum->lum_hash_type);
+	__swab32s(&lum->lum_type);
+	CLASSERT(offsetof(typeof(*lum), lum_padding1));
+}
+EXPORT_SYMBOL(lustre_swab_lmv_user_md);
+
 static void print_lum(struct lov_user_md *lum)
 {
 	CDEBUG(D_OTHER, "lov_user_md %p:\n", lum);
-- 
1.7.1

Re: [PATCH v2 30/58] staging: lustre: create striped directory

[Joe Perches]

On Tue, 2016-07-26 at 12:36 -0400, James Simmons wrote:
> From: wang di <di.wang@intel.com>
> 
> 1. client send create request to the master MDT, which
>   will allocate FIDs and create slaves. for all of slaves.
> 
> 2. Client needs to revalidate slaves during intent getattr
>    and open request.
> 
> 3. lmv_stripe_md will include attributes(size, nlink etc)
>    from all of stripe, which will be protected by UPDATE lock.
>    client needs to merge these attributes when update inode.
> 
> 4. send create request to the MDT where the file is located,
>    which can help creating master stripe of striped directory.
> 
> Changelog
> 
> v1) Original submitted patch
> 
> v2) fixed lmv_hash_fnv1a function to use do_div64 to fix
>     __umoddi3 undefined bug on 32 bit platforms.
> 
> Signed-off-by: wang di <di.wang@intel.com>
> Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-3529
> Reviewed-on: http://review.whamcloud.com/7196

Updated 	2 years, 5 months ago

how many of these old changes are yet to be integrated?

Re: [PATCH v2 30/58] staging: lustre: create striped directory

[James Simmons]

[-- Attachment #1: Type: text/plain, Size: 1766 bytes --]


> On Tue, 2016-07-26 at 12:36 -0400, James Simmons wrote:
> > From: wang di <di.wang@intel.com>
> > 
> > 1. client send create request to the master MDT, which
> >   will allocate FIDs and create slaves. for all of slaves.
> > 
> > 2. Client needs to revalidate slaves during intent getattr
> >    and open request.
> > 
> > 3. lmv_stripe_md will include attributes(size, nlink etc)
> >    from all of stripe, which will be protected by UPDATE lock.
> >    client needs to merge these attributes when update inode.
> > 
> > 4. send create request to the MDT where the file is located,
> >    which can help creating master stripe of striped directory.
> > 
> > Changelog
> > 
> > v1) Original submitted patch
> > 
> > v2) fixed lmv_hash_fnv1a function to use do_div64 to fix
> >     __umoddi3 undefined bug on 32 bit platforms.
> > 
> > Signed-off-by: wang di <di.wang@intel.com>
> > Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-3529
> > Reviewed-on: http://review.whamcloud.com/7196
> 
> Updated 	2 years, 5 months ago
> 
> how many of these old changes are yet to be integrated?

For the lnet/libcfs layer it is the lastest code so none.
For the lustre client code the further back you go the
more older patches are missing. The last 6 months I have
been filling in those gaps. Currently we are at the 2.5.58
version with this last code drop. As we approach the latest
release way less patches are needed to get caught up. Once
we get to the 2.6+ version of lustre the number of missing
patches should drop off greatly. Thats not to far away now.
I would estimate a few hundred patches are missing. Mind you
this is considering that larger patches need to be broken up.
For this last code drop 30 of the 50 patches was from an
original single large patch. 

Re: [PATCH 19/58] staging: lustre: llite: add md_op_data parameter to ll_get_dir_page

[Greg Kroah-Hartman]

On Thu, Jul 21, 2016 at 10:44:12PM -0400, James Simmons wrote:
> From: wang di <di.wang@intel.com>
> 
> Pass in struct md_op_data for ll_get_dir_page function.
> 
> Signed-off-by: wang di <di.wang@intel.com>
> Reviewed-on: http://review.whamcloud.com/7043
> Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-3531
> Reviewed-by: John L. Hammond <john.hammond@intel.com>
> Reviewed-by: Jinshan Xiong <jinshan.xiong@intel.com>
> Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
> Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
> Signed-off-by: James Simmons <jsimmons@infradead.org>
> ---
>  drivers/staging/lustre/lustre/llite/dir.c          |    8 ++++----
>  .../staging/lustre/lustre/llite/llite_internal.h   |    4 ++--
>  drivers/staging/lustre/lustre/llite/statahead.c    |   15 +++++++++++----
>  3 files changed, 17 insertions(+), 10 deletions(-)

This patch fails to apply, so I have to stop here in the patch series.

So I'm guesing your second patch series also will fail to apply, so can
you resend all of the outstanding patches you have sent me after
rebasing on my staging-testing branch?

thanks,

greg k-h

Re: [PATCH 19/58] staging: lustre: llite: add md_op_data parameter to ll_get_dir_page

[James Simmons]

> > From: wang di <di.wang@intel.com>
> > 
> > Pass in struct md_op_data for ll_get_dir_page function.
> > 
> > Signed-off-by: wang di <di.wang@intel.com>
> > Reviewed-on: http://review.whamcloud.com/7043
> > Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-3531
> > Reviewed-by: John L. Hammond <john.hammond@intel.com>
> > Reviewed-by: Jinshan Xiong <jinshan.xiong@intel.com>
> > Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
> > Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
> > Signed-off-by: James Simmons <jsimmons@infradead.org>
> > ---
> >  drivers/staging/lustre/lustre/llite/dir.c          |    8 ++++----
> >  .../staging/lustre/lustre/llite/llite_internal.h   |    4 ++--
> >  drivers/staging/lustre/lustre/llite/statahead.c    |   15 +++++++++++----
> >  3 files changed, 17 insertions(+), 10 deletions(-)
> 
> This patch fails to apply, so I have to stop here in the patch series.
> 
> So I'm guesing your second patch series also will fail to apply, so can
> you resend all of the outstanding patches you have sent me after
> rebasing on my staging-testing branch?

Do you mind if I combine them into one series? Also I have a few more 
patches I like to include. Is it okay to add those as well?

Re: [PATCH 19/58] staging: lustre: llite: add md_op_data parameter to ll_get_dir_page

[Greg Kroah-Hartman]

On Mon, Aug 15, 2016 at 10:40:29PM +0100, James Simmons wrote:
> 
> > > From: wang di <di.wang@intel.com>
> > > 
> > > Pass in struct md_op_data for ll_get_dir_page function.
> > > 
> > > Signed-off-by: wang di <di.wang@intel.com>
> > > Reviewed-on: http://review.whamcloud.com/7043
> > > Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-3531
> > > Reviewed-by: John L. Hammond <john.hammond@intel.com>
> > > Reviewed-by: Jinshan Xiong <jinshan.xiong@intel.com>
> > > Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
> > > Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
> > > Signed-off-by: James Simmons <jsimmons@infradead.org>
> > > ---
> > >  drivers/staging/lustre/lustre/llite/dir.c          |    8 ++++----
> > >  .../staging/lustre/lustre/llite/llite_internal.h   |    4 ++--
> > >  drivers/staging/lustre/lustre/llite/statahead.c    |   15 +++++++++++----
> > >  3 files changed, 17 insertions(+), 10 deletions(-)
> > 
> > This patch fails to apply, so I have to stop here in the patch series.
> > 
> > So I'm guesing your second patch series also will fail to apply, so can
> > you resend all of the outstanding patches you have sent me after
> > rebasing on my staging-testing branch?
> 
> Do you mind if I combine them into one series? Also I have a few more 
> patches I like to include. Is it okay to add those as well?

That's fine with me, send away!

greg k-h